World Indicators

Description: This project was created using Tableau & Python. In this project, I used various tools such as: Tableau:  Data cleaning,. Dashboards, Data visualization, Graphs, Calculated fields Python:  Codes and Libraries.

Title:

World Indicators

Project Overview:

Summery:

In this project, I used “Global Indicators” dataset. This dataset contains statistical information from various countries around the world across different years and includes indicators related to the economy, health, demographics, technology, the environment, and tourism.

I obtained the dataset from a Faradars educational course and analyzed it using “Tableau” and “Python”.  The analysis focuses on data from the years 2000 to 2012.

In general, analyzing global indicators serves two important purposes. First, it helps each country identify its strengths and weaknesses in areas such as economic growth, environmental sustainability, tourism development, and other key sectors. Second, it enables countries to compare their performance with other nations within the same continent or across different continents. Such comparisons provide valuable insights that support more effective planning and informed decision-making for sustainable development.

In my opinion, these comparative analyses can significantly assist governments in identifying opportunities and challenges, allowing them to develop more effective strategies for national growth and development.

Using Tableau, I leveraged data visualization techniques, calculated fields, and comparative charts to present the current status of the selected indicators and to generate forecasts for future trends. In addition, I used Python to develop computational algorithms and perform the analytical calculations required for the project.

Database:

Database contains the entities below:

There are two CSV files whose fields and records are as follows:

World Indicators; 18 fields & 2691 records

Country/Region:  Name of the country or region

Region:  Geographic region or continent

Year:  Year of data collection (2000-2012)

Birth Rate:  Number of births per 1,000 people

Business Tax Rate:  Percentage of taxes paid by businesses

CO2 Emissions:  Amount of carbon dioxide emissions

Days to Start Business:  Number of days required to start a business

Ease of Business:  Ease of Doing Business Index

Energy Usage:  Total energy consumption

GDP:  Gross Domestic Product (GDP)

Health Exp % GDP:  Health expenditure as a percentage of GDP

Health Exp/Capita:  Health expenditure per capita

Hours to do Tax:  Number of hours required to prepare and pay taxes

Infant Mortality Rate:  Number of infant deaths per 1,000 live births

Internet Usage:  Internet usage rate or number of users

Lending Interest:  Lending interest rate charged by financial institutions

Life Expectancy Female:  Average life expectancy of females

Life Expectancy Male:  Average life expectancy of males

World Indicators & Migrated Data; 12 fields & 2691 records

Mobile Phone Usage:  Mobile phone usage rate or subscriptions

Number of Records:  Record count (typically used for aggregation and analysis)

Population 0-14:  Population aged 0–14 years

Population 15-64:  Population aged 15–64 years (working-age population)

Population 65+:  Population aged 65 years and above

Population Total:  Total population

Population Urban:  Urban population

Tourism Inbound:  Revenue generated from international tourists visiting the country

Tourism Outbound:  Expenditure by residents traveling abroad

This dataset contains global indicators across several domains:

Economic Indicators:  GDP, Business Tax Rate, Ease of Business, Lending Interest.

Health Indicators:  Health Exp % GDP, Health Exp/Capita, Infant Mortality Rate, Life Expectancy (Female and Male).

Demographic Indicators:  Birth Rate, Population Total, Population Urban, Population Age Groups (0–14, 15–64, 65+)

Technology Indicators:  Internet Usage, Mobile Phone Usage, Environmental Indicators, CO2 Emissions, Energy Usage.

Tourism Indicators:  Tourism Inbound, Tourism Outbound.

Questions & Goals:

1-Data cleaning

2-Do countries with more favorable business environments also impose lower business tax rates?

3-Which countries and regions contribute most significantly to global economic output?

4-Which region contributes to 40% of the cumulative GDP performance?

5-Top 10 Countries by Average Working-Age Population to Average Elderly Population Ratio

6-What was the annual trend of average health expenditures in Iran as a percentage of GDP between 2000 and 2012?

7-Comparison of average life expectancy for women across six world regions

8-Correlation Analysis Between Internet Usage and Mobile Phone Usage

9-The relationship between health expenditure as a percentage of GDP and the infant mortality rate across different world regions from 2000 to 2012.

10-Comparative Analysis of International Tourism Flows by Country

11-Relationship between Energy Consumption and CO₂ Emissions Across Countries

12-Global Business Tax Rate Analysis & Bottom 10 Countries (Lowest Business Tax Rate)

Steps:

The dataset originally contained 27 fields, of which 24 represented global indicators for different countries. To make the analysis more structured and meaningful, I categorized these 24 indicators into five main groups:

• Economic Indicators
• Health Indicators
• Demographic Indicators
• Technology Indicators
• Environmental Indicators
• Tourism Indicators

This classification provided a clear framework for the analysis. I examined each group separately, beginning with the economic indicators, followed by the health, demographic, technology, environmental, and tourism indicators. Organizing the indicators into these categories made the analysis more systematic, improved the interpretation of the results, and facilitated comparisons across different dimensions of development.

Data Cleaning:

The first step of the project was to import the two CSV files into Tableau and perform an “inner join” to merge the datasets using their common fields. This ensured that only the records with matching values in both files were included in the analysis.

Ease of Business:  On the “Data Source” page, I changed the data type of the “Ease of Business” field from “String” to “Whole Number” to ensure that the data was correctly recognized as a numeric dimension.  This change enabled proper sorting, calculations, and analysis within Tableau.  In the “Data Pane”, the “Ease of Business” field was initially recognized as a “Dimension”. Since this field contains numerical values that should be analyzed, I converted it to a “Measure” to enable calculations, aggregations, and visual analysis in Tableau.

GDP:  The “Gross Domestic Product (GDP)” indicator was stored as whole numbers in the original dataset. However, Tableau automatically recognized it as a decimal (floating-point) data type. Therefore, I changed the data type to “Whole Number” to accurately reflect the nature of the data and ensure correct calculations and data presentation.

F28:  All values in this column were “NULL”.  Since the column contained no usable data, it was removed from the dataset during the data cleaning process.

Sorting:  The records in the dataset were initially unordered, and each country had multiple records corresponding to different years. To improve the organization of the data, I sorted the records first by “Country” and then by “Year”. As a result, each country’s records are grouped together in alphabetical order, with the corresponding years arranged sequentially. This sorting structure makes the dataset more organized and facilitates more efficient analysis and data exploration.

Finally, I saved the changes and prepared the tables for analysis.

Analysis:

After cleaning the data, I utilized the capabilities of Tableau and Python to answer the questions and achieve the intended objectives.

-Do countries with more favorable business environments also impose lower business tax rates?

This dashboard provides a comparative analysis of two important economic indicators across multiple countries:

-Ease of Business

-Business Tax Rate

The blue bars demonstrate substantial differences in the Ease of Business Index across countries.

Several countries, including Chile, Costa Rica, Bermuda, Burkina Faso, Cambodia, Djibouti, and Congo (Brazzaville), exhibit relatively high Ease of Business scores, whereas countries such as Austria, Aruba, and Curaçao display considerably lower values.

The orange bars reveal that Business Tax Rates also differ considerably.

While some countries maintain relatively low tax burdens, others impose substantially higher corporate taxes.  For example, Costa Rica and Congo (Brazzaville) show comparatively high tax rates.  Several countries with favorable business environments maintain moderate tax rates rather than extremely low ones.

This suggests that taxation alone does not determine the attractiveness of a country’s busines

This wide dispersion indicates that business regulations and administrative efficiency differ significantly from one country to another.

Business Tax Rates range from approximately 5% to nearly 190%.  However, most countries appear to cluster between 20% and 50%, indicating that extremely high business tax rates are relatively uncommon.  Only a small number of countries exhibit tax rates exceeding 100%, making them clear outliers within the dataset.

Ease of Business Does Not Increase as Tax Rates Decrease.  A visual comparison of the two measures suggests no strong linear relationship between Ease of Business and Business Tax Rate.  For example:

Several countries with Ease of Business scores above 170 still maintain moderate to high tax rates (40–90%).

Conversely, some countries with low tax rates (below 20%) record only moderate Ease of Business scores (40–80).

This indicates that taxation alone does not explain differences in business performance.

High Dispersion Indicates Structural Differences.  The blue bars (Ease of Business) exhibit noticeably greater dispersion than the orange bars (Business Tax Rate).

This suggests that institutional quality, administrative efficiency, and regulatory frameworks differ more substantially across countries than tax policies alone.

Outlier Countries:

Several countries stand out as outliers because they combine exceptionally high Ease of Business scores with either very high or very low Business Tax Rates.

These cases imply that national competitiveness is influenced by multiple factors, including:

-Regulatory efficiency

-Government effectiveness

-Digital public services

-Legal protection

-Access to finance

-rather than taxation alone.

-Which countries and regions contribute most significantly to global economic output?

This dashboard presents a Pareto analysis of Average Gross Domestic Product (GDP) across countries grouped by world regions. The blue bars represent the average GDP of individual countries, while the orange line illustrates the cumulative contribution of GDP to the overall total.

To create the “Pareto chart” and properly configure its axes, I created a “calculated field” named “Cumulative % of Average GDP”. This calculated field was used to display the cumulative percentage of the average GDP, enabling the Pareto analysis and improving the accuracy of the chart’s secondary axis.

The Americas Lead Global Economic Performance.  The Americas record the highest average GDP of 470.59 billion USD, accounting for 32.76% of the combined average GDP across all regions.  This indicates that countries within the Americas have the strongest average economic output among the six regions.

Asia Holds the Second Position.  Asia ranks second with an average GDP of 384.18 billion USD, contributing 26.74% of the total.  Together, The Americas and Asia account for 59.50% of the overall average GDP, demonstrating that nearly three-fifths of global average economic output is concentrated in these two regions.

Europe Completes the Top Three.  Europe records an average GDP of 356.61 billion USD, representing 24.82% of the total.  After Europe is included, the cumulative contribution reaches 84.33%, meaning that the top three regions contribute more than four-fifths of the total average GDP.  This pattern closely reflects the Pareto Principle, where a limited number of groups account for the majority of total economic output.

Middle East Represents a Moderate Contributor.  The Middle East reports an average GDP of 116.88 billion USD, contributing 8.14% to the total.  Although significantly lower than the top three regions, it remains substantially ahead of Africa.

Oceania and Africa Contribute the Smallest Shares.  Oceania records an average GDP of 84.26 billion USD, accounting for 5.87% of the total.  Africa ranks last with an average GDP of only 24.04 billion USD, contributing just 1.67%..  The difference between the Americas and Africa exceeds 446 billion USD, highlighting a substantial disparity in regional economic capacity.

Overall, the dashboard demonstrates a pronounced concentration of economic output across world regions. The Americas rank first with an average GDP of 470.59 billion USD (32.76%), followed by Asia (384.18 billion USD; 26.74%) and Europe (356.61 billion USD; 24.82%). Collectively, these three regions contribute 84.33% of the total average GDP, while the Middle East, Oceania, and Africa together account for only 15.67%. The Pareto visualization effectively emphasizes the unequal distribution of economic capacity and provides valuable insights for regional economic analysis and strategic decision-making.

-Which region contributes to 40% of the cumulative GDP performance?

A 40% Reference Line has been added to establish a performance threshold, allowing decision-makers to identify where cumulative economic contribution surpasses this benchmark.  The majority of countries contributing to the first 40% are located within The Americas and Asia.  These regions contain the world’s largest economies and therefore dominate global GDP.  The steep slope of the Pareto curve before the reference line confirms this concentration

Countries Contributing to the First 40% of Cumulative GDP;

The 40% cumulative threshold is reached primarily by three major economies:

United States

China

Japan

Although these countries appear multiple times because the dataset contains observations for multiple years, they consistently dominate the global GDP ranking throughout the study period.

The United States contributes the largest share, with annual GDP values ranging from approximately 10.3 to 16.2 trillion USD. China follows with GDP values between 4.5 and 8.2 trillion USD, while Japan contributes between 4.2 and 5.9 trillion USD.  Together, these three economies account for approximately 40% of the cumulative GDP represented in the visualization, highlighting their dominant role in the global economy.

-Top 10 Countries by Average Working-Age Population to Average Elderly Population Ratio

To analyze this metric, I created a Butterfly Chart and used a calculated field to properly structure the chart and align the two sides for effective comparison.

This dashboard compares the average proportion of the working-age population (15–64 years) with the average proportion of the elderly population (65 years and above) across selected countries. The mirrored bar chart provides a clear comparison between economically active populations and aging populations, helping identify countries with favorable labor-force structures and those facing demographic aging.

Countries with the Largest Working-Age Population:  The United Arab Emirates records the highest average working-age population, at approximately 80.4% of its total population. This is closely followed by Qatar, with a similarly high proportion.

Other countries with a relatively large working-age population include:

Macao SAR, Hong Kong SAR, Singapore, Bahrain

These economies benefit from a large labor force, which supports productivity and economic growth.

Countries with the Largest Elderly Population:  On the opposite side of the chart, Hong Kong SAR exhibits the highest average elderly population, with approximately 12.2% of its population aged 65 years or older.

Other countries with relatively high aging populations include:

Slovakia, South Korea, Singapore, China

These countries are experiencing demographic aging and may face increasing pressure on healthcare systems and pension programs.

Young Workforce Economies:  The United Arab Emirates, Qatar, Bahrain, and Kuwait display a combination of:

High working-age population (approximately 75–80%)

Low elderly population (generally below 6%)

This demographic profile indicates a strong labor force and is often associated with labor migration and expanding economies.

Aging Economies:  Countries such as Hong Kong SAR, Singapore, South Korea, China, and Slovakia have noticeably higher shares of elderly citizens while maintaining comparatively smaller working-age populations.  This reflects the later stages of demographic transition and suggests increasing dependency ratios over time.  The visualization reveals a clear demographic contrast.

Younger Workforce Countries, Aging Population Countries, United Arab Emirates Hong Kong SAR, Qatar   Slovakia, Bahrain,     South Korea, Kuwait Singapore, Macao SAR, China

The first group enjoys a demographic advantage through a larger labor force, whereas the second group faces the economic implications of population aging.

-What was the annual trend of average health expenditures in Iran as a percentage of GDP between 2000 and 2012?

This dashboard illustrates the annual trend of Iran’s average health expenditure as a percentage of GDP between 2000 and 2012. The visualization combines lollipop markers and a color gradient to emphasize fluctuations in healthcare spending over time. Green circles represent higher expenditure levels, while red circles indicate lower levels.

1. Peak Health Expenditure:

The highest healthcare expenditure occurred in 2010, reaching approximately 7.3% of GDP.

Similarly,

2009: 7.2%

2011: 6.8%

2012: 6.7%

These years represent the strongest commitment to healthcare investment during the period analyzed.

. Lowest Health Expenditure

The lowest value is observed in 2000, where health expenditure accounted for only 4.6% of GDP.

Other relatively low values include:

2003: 4.7%

2004: 4.7%

2005: 5.3%

3. Overall Growth

Between 2000 and 2010, healthcare expenditure increased from:

4.6% to 7.3%

This represents an increase of approximately 2.7 percentage points, or about 59% relative growth over the decade.

4. Slight Decline After the Peak

Following the peak in 2010, healthcare expenditure declined modestly:

2011: 6.8%

2012: 6.7%

Although spending decreased slightly, it remained well above the levels observed in the early 2000s.

The visualization indicates that Iran gradually allocated a larger share of its GDP to healthcare throughout most of the study period. Increased healthcare investment is generally associated with improvements in medical infrastructure, public health services, and access to healthcare.

However, the slight decline after 2010 may suggest fiscal constraints, changes in government priorities, or broader economic conditions affecting public expenditure.

From a policy perspective, the dashboard demonstrates a significant expansion in healthcare investment over the study period. The increase from 4.6% to 7.3% of GDP reflects stronger governmental support for the healthcare sector. The subsequent stabilization around 6.7–6.8% indicates that, although expenditure decreased slightly after its peak, healthcare remained a major component of national spending.

-Comparison of average life expectancy for women across six world regions

The waterfall chart compares the average female life expectancy across the six world regions and illustrates how each region contributes to the cumulative value of this indicator.

The Americas record the highest average female life expectancy, at approximately 79.8 years, making the largest contribution to the cumulative total. This reflects the region’s strong healthcare systems, higher living standards, and broader access to medical services.

Oceania ranks second, with an average life expectancy of approximately 74–75 years, indicating favorable healthcare outcomes and a high quality of life.

Europe also demonstrates a high average female life expectancy, close to 79 years, highlighting the effectiveness of its healthcare systems, advanced medical technology, and strong public health policies.

The Middle East records an average female life expectancy of approximately 72–74 years, representing a moderate to high level of health performance across the region.

Asia has an average life expectancy of approximately 70–72 years. Although the regional average is moderate, considerable variation exists between developed and developing countries within the continent.

Africa records the lowest average female life expectancy, at 57.16 years, which is approximately 22–23 years lower than the Americas. This significant gap reflects disparities in healthcare access, economic development, disease burden, and social conditions.

-Correlation Analysis Between Internet Usage and Mobile Phone Usage

The scatter plot examines the relationship between average Internet usage and average mobile phone usage across countries. Each data point represents an individual country, while the fitted regression line illustrates the overall trend between the two digital indicators.  The upward slope of the regression line clearly indicates a strong positive linear relationship between Internet usage and mobile phone usage. As Internet adoption increases, mobile phone usage also tends to increase, suggesting that these two indicators evolve together as countries advance in digital development.  The calculated coefficient of determination (R² = 0.7927) indicates that approximately 79.27% of the variation in mobile phone usage is explained by Internet usage. This represents a high level of explanatory power, demonstrating that Internet accessibility is one of the most influential factors affecting mobile technology adoption across countries.  The remaining 20.73% of unexplained variation may result from additional socioeconomic and technological factors, including:

Income level and purchasing power

Telecommunications infrastructure quality

Urbanization rate

Government digital transformation policies

Population density

Smartphone affordability

Educational attainment

Market competition among mobile network providers

Although the majority of observations closely follow the regression line, several countries deviate from the overall pattern. These outliers indicate that some nations experience either higher or lower mobile phone adoption than expected based solely on Internet usage. Such deviations may reflect differences in regulatory environments, technology investment, affordability of digital services, or unique demographic characteristics.

Another notable observation is that the spread of data points becomes slightly wider at higher Internet usage levels. This suggests that while Internet access remains a major driver of mobile phone usage, other country-specific factors become increasingly important as digital markets mature.

Overall, the regression model demonstrates a statistically meaningful and practically significant relationship between Internet usage and mobile phone usage. The results support the view that expanding Internet accessibility is strongly associated with greater adoption of mobile technologies and broader digital inclusion.

From a business perspective, the findings indicate that Internet infrastructure development plays a critical role in expanding mobile technology adoption. Countries with stronger Internet penetration generally create more favorable conditions for digital services, mobile applications, e-commerce, online banking, and digital communication.

The analysis also suggests that policymakers and telecommunications providers should consider Internet expansion as a strategic investment that can generate long-term economic and technological benefits. At the same time, the presence of outliers highlights the importance of considering local economic conditions and regulatory environments when designing digital development strategies.  The analysis confirms a strong positive relationship between Internet usage and mobile phone usage. With an R² value of 79.27%, Internet usage explains most of the observed variation in mobile phone adoption across countries. However, complementary factors such as economic development, infrastructure quality, affordability, and public policy remain important contributors and should be incorporated into future analyses to obtain a more comprehensive understanding of digital adoption.

-The relationship between health expenditure as a percentage of GDP and the infant mortality rate across different world regions from 2000 to 2012.

This scatter plot explores the relationship between health expenditure as a percentage of GDP and the infant mortality rate across different world regions from 2000 to 2012.

Overall, the visualization suggests a negative relationship between healthcare investment and infant mortality. Countries allocating a higher percentage of GDP to healthcare generally experience lower infant mortality rates, although the strength of this relationship varies across regions.

Several important observations can be made:

European countries are highly concentrated in the lower-right portion of the chart, indicating relatively high healthcare expenditure accompanied by consistently low infant mortality. This reflects mature healthcare systems and effective public health policies.

African countries exhibit the widest dispersion and the highest infant mortality rates. Many African countries spend a relatively small share of GDP on healthcare while still experiencing significantly higher infant mortality, suggesting that limited healthcare resources and broader socioeconomic challenges continue to affect health outcomes.

Asian countries display considerable variation. Some countries achieve low infant mortality with moderate healthcare spending, whereas others continue to experience higher mortality despite increased expenditure. This indicates that healthcare spending alone does not fully determine health performance.

The Americas, Oceania, and the Middle East generally occupy middle to upper expenditure levels with relatively moderate infant mortality, although several outliers remain.

The presence of a few outlier countries with unusually high healthcare expenditure but only moderate improvements in infant mortality implies that increasing healthcare spending alone may not immediately translate into better outcomes. Efficiency of spending, healthcare accessibility, education, sanitation, and maternal healthcare also play critical roles.

Using the Year filter, users can observe how countries gradually shift toward lower infant mortality over time, indicating improvements in global healthcare systems and public health interventions between 2000 and 2012.

This dashboard provides a comparative analysis of inbound and outbound tourism across major countries while simultaneously illustrating each country’s tourism balance through color encoding. By combining two synchronized bar charts with a diverging color scale, the visualization enables a comprehensive evaluation of international tourism performance and travel behavior.

The upper panel represents inbound tourism, indicating the volume of international visitors received by each country, whereas the lower panel displays outbound tourism, representing residents traveling abroad. Together, these measures reveal whether countries primarily function as tourism destinations or as major sources of international travelers.

The United States stands out as the strongest inbound tourism destination among all selected countries, recording approximately 25 trillion in inbound tourism value. This dominant position reflects its globally diversified tourism market, international business activities, entertainment sector, extensive transportation infrastructure, and worldwide accessibility.

European countries including France, Spain, Italy, Germany, and the United Kingdom consistently rank among the leading tourism markets. Their strong inbound tourism performance can largely be attributed to rich cultural heritage, historical attractions, developed transportation systems, and mature tourism industries.

A notable observation is that Germany and the United Kingdom exhibit exceptionally high outbound tourism compared with many other countries. This suggests that residents in these countries possess substantial purchasing power and demonstrate a high propensity for international travel. Consequently, these countries generate significant tourism expenditures abroad.

Japan presents an interesting tourism profile. While its inbound tourism remains moderate relative to the leading destinations, outbound tourism is considerably higher, indicating that Japan acts as a strong outbound tourism market with substantial international travel demand from its residents.

The color encoding based on Tourism Balance significantly enhances analytical capability. Countries shaded toward cooler colors indicate relatively positive tourism balances, where inbound tourism exceeds outbound tourism. Conversely, warmer colors identify countries whose outbound tourism expenditures are relatively higher than tourism revenues received from foreign visitors. This additional analytical layer enables rapid identification of tourism surplus and deficit economies without requiring additional calculations.

Another important pattern revealed by the dashboard is the concentration of global tourism flows. Only a small group of countries accounts for the majority of international tourism activity, while the remaining countries contribute relatively small tourism volumes. Such concentration reflects disparities in economic development, tourism infrastructure, international connectivity, destination attractiveness, political stability, visa policies, and investment in tourism services.

Furthermore, noticeable differences between inbound and outbound tourism highlight the varying economic roles countries play within the global tourism market. Some countries specialize in attracting foreign visitors, whereas others primarily generate outbound tourism demand through their residents’ international travel.

Overall, the dashboard effectively combines comparative analysis, tourism balance assessment, and ranking visualization into a single analytical view, providing valuable insights for policymakers, tourism authorities, investors, and destination management organizations seeking to improve tourism competitiveness and maximize economic benefits.

The clustering analysis segmented the 20 selected countries into four distinct groups based on three tourism indicators: Tourism Inbound, Tourism Outbound, and Tourism Balance. All variables were normalized before clustering to ensure that differences in measurement scales did not influence the results.

The clustering algorithm produced a Between-group Sum of Squares of 2.991 and a Within-group Sum of Squares of 0.622, indicating that most of the variation exists between clusters rather than within them. This suggests that the clustering model successfully identified meaningful and well-separated groups of countries with similar tourism characteristics.

Cluster 1 – Global Tourism Leader

Number of countries: 1

Average Tourism Inbound: 23.82 trillion

Average Tourism Outbound: 5.67 trillion

Tourism Balance: +1.51 trillion

Cluster 1 contains only one country, representing a clear outlier with exceptionally high inbound tourism. The extremely large inbound tourism compared with outbound tourism indicates a country that functions as a dominant global tourism destination while maintaining a strong positive tourism balance. Based on the previous visualization, this cluster most likely represents the United States.

Cluster 2 – Moderate Tourism Economies

Number of countries: 12

Average Tourism Inbound: 2.79 trillion

Average Tourism Outbound: 1.80 trillion

Tourism Balance: +0.98 trillion

This is the largest cluster, containing 60% of all analyzed countries. These countries exhibit balanced tourism systems with moderate inbound and outbound tourism. Their positive tourism balance suggests that they receive more tourism revenue than they spend abroad. They represent stable and mature tourism markets with consistent international competitiveness.

Cluster 3 – Strong Tourism Destinations

Number of countries: 4

Average Tourism Inbound: 7.63 trillion

Average Tourism Outbound: 4.91 trillion

Tourism Balance: +2.55 trillion

Countries in this cluster are major international tourism destinations. They generate high inbound tourism while maintaining substantial outbound tourism. The highest positive tourism balance among all clusters indicates that tourism contributes significantly to their national economies.

Cluster 4 – Tourism Deficit Countries

Number of countries: 3

Average Tourism Inbound: 5.14 trillion

Average Tourism Outbound: 9.69 trillion

Tourism Balance: −5.01 trillion

This cluster contains countries with the largest tourism deficits. Outbound tourism greatly exceeds inbound tourism, indicating that residents spend considerably more on international travel than foreign visitors contribute to the domestic tourism sector. These countries represent strong outbound tourism markets rather than major tourism destinations.

-Relationship between Energy Consumption and CO₂ Emissions Across Countries

The scatter plot demonstrates the relationship between Energy Usage and CO₂ Emissions across different world regions. Marker size represents Population Total, while colors distinguish geographical regions. Separate trend lines are displayed for each region to highlight regional differences in the relationship.

Key Findings

1. Strong Positive Linear Relationship

The visualization clearly shows a strong positive linear relationship between energy consumption and CO₂ emissions.

As energy usage increases, CO₂ emissions increase almost proportionally across all regions. This indicates that fossil-fuel-based energy production remains the dominant source of greenhouse gas emissions worldwide.

2. Regional Differences

Although every region follows the same general trend, noticeable differences exist in the slope of the regression lines.

Asia exhibits the steepest regression line, suggesting that increases in energy consumption lead to larger increases in CO₂ emissions compared with other regions.

Africa and Europe display flatter regression lines, indicating relatively lower emission growth for similar increases in energy consumption.

Oceania and the Middle East lie between these two extremes.

These differences may reflect variations in

energy mix,

industrial structure,

efficiency,

environmental regulations,

renewable energy adoption.

3. Population Effect

Marker size represents total population.

Large-population countries are concentrated in the upper-right portion of the chart, indicating simultaneously high

energy consumption,

CO₂ emissions,

population.

This suggests that population size is an important driver of national energy demand.

However, population alone does not explain emissions, since countries with similar populations may have different emission levels depending on their energy efficiency.

4. High-Consumption Outliers

Several countries appear in the upper-right corner.

These countries consume substantially more energy and produce much larger CO₂ emissions than the majority of observations.

These observations likely represent major industrial economies and therefore deserve additional investigation.

5. Consistency of the Trend

The regional regression lines remain nearly parallel.

This indicates that the relationship between energy use and emissions is relatively stable across different parts of the world.

Although the emission intensity differs slightly among regions, the overall relationship remains highly consistent.

Business & Policy Implications

The dashboard suggests several strategic insights:

Increasing energy consumption generally leads to increased CO₂ emissions.

Improving energy efficiency can reduce emissions without reducing economic activity.

Expanding renewable energy sources can flatten regional regression lines.

High-population countries should prioritize sustainable energy policies.

Regions with steeper slopes should invest more heavily in clean technologies.

Linear Regression Analysis Using Python (TabPy)

To gain deeper insights into the relationship between Energy Usage and CO₂ Emissions, a Linear Regression model was implemented using Python (scikit-learn) through TabPy instead of relying solely on Tableau’s built-in trend line.

The regression model estimates the best-fitting line that minimizes the prediction error between observed and predicted CO₂ emissions.

Model Interpretation

The model demonstrates that Energy Usage is a strong predictor of CO₂ Emissions.

As energy consumption increases, predicted CO₂ emissions also increase almost linearly, confirming a strong positive relationship.

Residual Analysis

The Python script calculates the Residual for every observation.

Residual is defined as:

Residual = |Actual CO₂ − Predicted CO₂|

A small residual means that the country behaves exactly as expected according to the regression model.

A large residual indicates that the country’s emissions differ significantly from what the model predicts.

Interpretation of Large Residuals

Countries with larger residual values may indicate:

Higher dependence on fossil fuels

Low energy efficiency

Heavy industrial activities

Limited adoption of renewable energy

Unique environmental or economic conditions

These observations deserve further investigation because they behave differently from the overall global pattern.

Interpretation of Small Residuals

Countries with low residual values closely follow the global regression model.

This suggests that their relationship between energy consumption and CO₂ emissions is consistent with worldwide trends.

Value of Python Integration

Using Python with Tableau provides several advantages:

Machine Learning inside Tableau

More flexible statistical analysis

Automatic residual calculation

Capability to implement advanced predictive models

Better identification of abnormal observations (outliers)

Business Insight

The regression model can be used to:

Predict future CO₂ emissions

Detect abnormal countries

Compare regional efficiency

Support environmental decision making

Evaluate sustainability policies

A Linear Regression model was implemented in Python using “tabpy” to estimate CO₂ emissions based on energy consumption. The predicted values closely follow the observed values, indicating that the model successfully captures the relationship between energy usage and carbon emissions. This demonstrates that energy consumption is a strong predictor of CO₂ emissions across countries.

This dashboard investigates the relationship between Energy Usage and CO₂ Emissions by combining traditional Tableau visualization with a Python-based Linear Regression model executed through TabPy. The objective is not only to visualize historical data but also to estimate expected CO₂ emissions based on energy consumption.

Overall Relationship

The scatter plot reveals a strong positive linear relationship between energy consumption and carbon dioxide emissions. As countries consume more energy, their CO₂ emissions increase almost proportionally.

The prediction lines generated by the machine learning model closely follow the actual observations, indicating that energy usage is an effective predictor of carbon emissions.

Machine Learning Prediction

Unlike Tableau’s built-in trend line, the prediction line shown in this dashboard is generated using a Linear Regression model developed in Python and executed through TabPy.

The model learns the relationship

Energy Usage → Expected CO₂ Emissions

using historical observations.

For every country, the model estimates the amount of CO₂ that should be emitted according to its energy consumption.

Regional Comparison

The prediction lines are displayed separately for each geographical region.

Asia

Asia exhibits the steepest prediction line.

This suggests that, on average, an increase in energy consumption produces a larger increase in CO₂ emissions than in other regions.

The largest bubbles also belong to Asian countries, reflecting their large populations and intensive industrial activity.

Europe

European countries generally follow a prediction line with a slightly lower slope.

This indicates relatively better energy efficiency and lower carbon emissions for comparable levels of energy usage.

Africa

African countries are concentrated near the lower-left corner.

Their low energy consumption corresponds to relatively low CO₂ emissions.

The Americas

Countries in the Americas demonstrate a strong linear relationship with moderate prediction slopes.

The observed values closely match the predicted values, indicating consistent emission behavior.

Oceania

Although represented by fewer observations, Oceania follows the same overall trend and aligns closely with the regression model.

Middle East

The Middle East displays relatively high CO₂ emissions compared with its energy consumption.

ts prediction line is steeper than Europe’s but lower than Asia’s, suggesting comparatively higher carbon intensity.

Prediction Accuracy

The actual observations are located very close to the prediction lines.

This indicates that the Linear Regression model captures most of the variation in CO₂ emissions.

The relatively small residuals suggest good predictive performance.

Population Effect

Bubble size represents total population.

Large-population countries are concentrated in the upper-right section of the chart, indicating that countries with larger populations generally consume more energy and consequently emit more CO₂.

However, the prediction model demonstrates that energy consumption, rather than population alone, is the primary explanatory variable for carbon emissions.

Business and Policy Insights

The model provides several practical insights:

Energy consumption is a reliable predictor of carbon emissions.

Regional differences indicate varying levels of energy efficiency.

Asian countries show the highest expected growth in emissions if energy consumption continues to rise.

European countries demonstrate comparatively better environmental efficiency.

Policymakers can use the prediction model to estimate future emissions under different energy consumption scenarios.

Governments can evaluate whether a country’s actual emissions exceed the predicted level and identify opportunities to improve energy efficiency.

This visualization presents the predicted CO₂ emissions generated by a Python-based Linear Regression model integrated into Tableau through TabPy. Unlike descriptive dashboards, this chart demonstrates the predictive capability of machine learning by estimating future or expected CO₂ emissions from energy consumption.

Model Performance

The predicted values form a clear upward linear pattern, confirming that the regression model successfully learned the relationship between energy usage and CO₂ emissions.

The smooth distribution of the predicted points indicates that the model produces consistent estimates without irregular fluctuations.

Trend Analysis

The chart reveals three distinct ranges of energy consumption:

Low Energy Consumption (0–5 million): Most countries are concentrated in this range, with predicted emissions remaining relatively low.

Medium Energy Consumption (5–15 million): Predicted emissions increase steadily, reflecting the model’s linear relationship.

High Energy Consumption (15–32 million): Countries with higher energy demand are predicted to produce significantly higher CO₂ emissions, reaching approximately 90–95 million units.

This demonstrates that increases in energy usage are accompanied by proportional increases in predicted emissions.

Prediction Reliability

The predicted observations follow a nearly perfect linear trajectory.

This indicates that the Linear Regression model is stable and that energy consumption explains a large proportion of the variation in CO₂ emissions.

The absence of abrupt deviations suggests that the relationship between the two variables is highly consistent within the dataset.

Country-Level Interpretation

Each point represents a specific country in a particular year.

As countries move toward higher energy consumption levels, the model predicts corresponding increases in carbon emissions.

Countries positioned in the upper-right corner represent economies with intensive industrial activities and high energy demand.

Temporal Perspective

Since Year is included in the level of detail, the prediction is generated separately for each country-year observation.

This enables analysts to monitor how predicted CO₂ emissions evolve over time as energy consumption changes, making the model suitable for longitudinal analysis rather than a single aggregated estimate.

Practical Applications

This predictive model can support:

Estimating future carbon emissions under different energy consumption scenarios.

Evaluating the environmental impact of increasing energy demand.

Comparing actual emissions with model expectations to identify unusually efficient or inefficient countries.

Supporting environmental policy planning and sustainability initiatives.

Building early-warning systems for carbon emission management.

-Global Business Tax Rate Analysis & Bottom 10 Countries (Lowest Business Tax Rate)

This dashboard provides a global comparison of Business Tax Rates across different countries using an interactive choropleth map. The color gradient highlights the variation in tax rates, allowing users to quickly identify countries with relatively high and low business taxation.

The analysis reveals a significant variation in tax policies worldwide. Countries with the highest business tax rates (such as Greenland, Country A, and Country B) are represented by the darkest shades on the map, indicating a heavier tax burden on businesses. Higher tax rates may increase government revenue but can also reduce business competitiveness and discourage foreign direct investment if not balanced with supportive economic policies.

In contrast, countries with the lowest business tax rates (such as Argentina, Country C, and Country D) appear in lighter shades. Lower tax rates can make these countries more attractive for investment and business expansion; however, governments may rely on alternative sources of public revenue to finance infrastructure and public services.

The dashboard also demonstrates clear regional differences in taxation, suggesting that fiscal policies are influenced by each country’s economic development, investment strategy, and government priorities.

By combining geographic visualization with tax information, decision-makers can easily identify regions with favorable tax environments and compare international taxation patterns for investment planning and economic analysis.

Global Analysis

The map reveals substantial variation in business tax rates worldwide, indicating that taxation policies differ significantly across regions.

Overall, Countries with lighter colors generally impose lower business tax rates, creating a more attractive environment for investment and business expansion.

Countries with darker colors tend to apply higher tax rates, which may increase operating costs but often support stronger public infrastructure and government services.

Regional Analysis

North America

The United States and Canada exhibit moderate to relatively high business tax rates, reflecting a balance between government revenue generation and economic competitiveness.

Europe

Most European countries fall within the medium tax range. Higher taxation is often accompanied by advanced infrastructure, stable institutions, and high-quality public services.

Asia

Asia demonstrates considerable variation. Several emerging economies maintain relatively low tax rates to attract foreign investment, whereas developed economies generally apply higher tax rates.

Africa

African countries display diverse taxation policies. Some countries offer lower tax rates to encourage economic development, while others rely more heavily on taxation due to economic structure and fiscal requirements.

South America

Business tax rates across South America remain generally moderate, although noticeable differences exist among countries, reflecting diverse fiscal policies.

Interactive Parameter

The Country/Region Parameter allows users to dynamically select individual countries for focused analysis, improving comparisons and supporting interactive exploration.

Business Insights

This dashboard supports decision-making by helping organizations:

Compare international taxation policies.

Identify investment-friendly countries.

Evaluate regional fiscal competitiveness.

Support global business expansion strategies.

-Bottom 10 Countries (Lowest Business Tax Rate)

The countries with the lowest business tax rates include United Arab Emirates, Bahrain, Qatar, Kuwait, Oman, Saudi Arabia, Singapore, Hong Kong SAR, Maldives, and Brunei Darussalam. Lower tax rates create a more favorable environment for business development by reducing financial pressure on companies. These countries often attract higher levels of foreign direct investment (FDI), encourage entrepreneurship, and improve overall economic competitiveness through business-friendly fiscal policies.

-Top 10 Countries (Highest Business Tax Rate)

Congo records the highest Business Tax Rate in the dataset, indicating a relatively heavy tax burden on businesses. Such a high tax rate may increase operational costs and reduce the country’s attractiveness for domestic and foreign investment unless it is supported by efficient public services, stable regulations, and adequate infrastructure.

The countries with the highest business tax rates include Comoros, Belarus, Sierra Leone, Algeria, Argentina, Brazil, Bolivia, Uzbekistan, Mauritania, and Chad. These countries impose relatively high tax burdens on businesses, which can increase operating costs and reduce profitability. High business tax rates may discourage entrepreneurship, limit private sector growth, and decrease the attractiveness of these countries to foreign investors. As a result, governments should carefully balance tax revenue generation with maintaining a competitive business environment.

The Business Tax Rate dashboard presents a global comparison of business tax rates using a choropleth map, where darker colors indicate higher tax rates and lighter colors represent lower tax rates. The visualization reveals significant geographical differences in tax policies across countries.

The analysis indicates that several countries in Africa and South America tend to have relatively higher business tax rates, whereas many countries in the Middle East and parts of Asia maintain comparatively lower tax rates. This variation reflects different economic strategies, fiscal policies, and approaches to attracting domestic and international investment.

Countries with high tax rates may generate greater government revenue in the short term; however, excessive taxation can reduce business competitiveness and discourage new investment. Conversely, countries with lower tax rates often foster a more attractive business environment by encouraging entrepreneurship, supporting private sector growth, and increasing foreign investment.

Overall, the dashboard demonstrates that business tax policy plays a crucial role in shaping the investment climate and economic performance of countries around the world. Comparing the highest and lowest tax-rate countries provides valuable insights into how fiscal policy can influence economic development and business competitiveness.

Key points:

• The dashboard demonstrates that Ease of Business and Business Tax Rate are not strongly correlated across countries. Although taxation remains an important economic factor, business competitiveness is largely determined by the quality of institutions, regulatory efficiency, and the overall ease of operating a business. This visualization reinforces the importance of adopting a multidimensional approach when evaluating national economic performance and investment attractiveness.
• The analysis suggests that the largest consumer markets and strongest economic activity are concentrated within The Americas, Asia, and Europe. These regions provide greater opportunities for investment, international trade, industrial development, and business expansion.  Conversely, Africa and Oceania exhibit considerably lower average GDP values. While their current economic scale is smaller, they may offer long-term growth opportunities as emerging markets.
• The 40% Reference Line serves as a strategic benchmark.  Its position indicates that:

Approximately 40% of the cumulative average GDP is generated by only a limited number of countries.  The remaining 60% is distributed across a much larger number of countries.  This reflects a strong concentration of global economic activity within a relatively small group of high-performing economies.  The reference line therefore highlights the unequal distribution of economic output and helps decision-makers identify the point at which the largest contributors have already been accounted for.

• The dashboard demonstrates that the United Arab Emirates and Qatar maintain the strongest demographic advantage due to their exceptionally high working-age populations, exceeding 80% and 79%, respectively. Meanwhile, Hong Kong SAR records the highest share of elderly residents at approximately 12.2%, followed by Slovakia and South Korea. These demographic differences have important implications for labor market dynamics, economic growth, healthcare planning, and long-term social policy.
• The health expenditure dashboard reveals a clear upward trend in Iran’s health spending (as a percentage of GDP) between 2000 and 2010, followed by a slight decline through 2012. The data indicate sustained investment in the health sector, with expenditure rising by approximately 59 percent during this period before stabilizing at a relatively high level.
• The results reveal substantial regional differences in female life expectancy worldwide. The Americas, Europe, and Oceania demonstrate the highest average life expectancy, reflecting stronger healthcare systems, better economic conditions, and broader access to quality medical services. In contrast, Africa records the lowest average of 57.16 years, approximately 28% lower than the Americas. These findings highlight the need for increased investment in healthcare infrastructure, disease prevention, maternal and child health services, and equitable access to healthcare in lower-performing regions.
• Internet usage is a major determinant of mobile phone adoption across countries.  The R² value of 79.27% demonstrates the strong explanatory power of the regression model.  Investments in broadband infrastructure and digital connectivity are likely to accelerate mobile technology adoption and support digital transformation.  Policymakers should investigate countries that deviate from the general trend to identify structural challenges or successful digital strategies that can inform future policy decisions.
• The analysis indicates that increasing healthcare investment is generally associated with lower infant mortality; however, financial investment alone is insufficient. Sustainable improvements require efficient healthcare management, equitable access to medical services, maternal and child healthcare programs, and broader socioeconomic development. Policymakers should therefore focus not only on increasing healthcare expenditure but also on improving the effectiveness and quality of healthcare delivery.
• The clustering analysis reveals four distinct tourism market profiles:

A single global tourism leader with exceptionally high inbound tourism.

A large group of balanced tourism economies with stable positive tourism balances.

A group of internationally competitive tourism destinations generating substantial tourism surpluses.

A small group of countries characterized by high outbound tourism and negative tourism balances.

The relatively low Within-group Sum of Squares compared with the Between-group Sum of Squares indicates good cluster separation, suggesting that the selected variables effectively distinguish different tourism market structures.

Overall, the clustering results provide valuable insights for tourism policy development, investment prioritization, destination marketing, and international tourism competitiveness assessment.

• There is a clear positive relationship between Energy Usage and CO₂ Emissions.

Asia contains the countries with the highest levels of both variables.

Africa generally exhibits the lowest energy consumption and carbon emissions.

Larger populations are generally associated with higher emissions, although technology and energy policy significantly influence outcomes.

Regional trend lines suggest differences in energy efficiency and environmental performance.

• Regional differences exist, but every region follows the same fundamental pattern: greater energy consumption is associated with greater carbon emissions.  The visualization highlights the importance of improving energy efficiency and accelerating the transition toward cleaner energy sources to achieve sustainable development goals.
• The integration of Tableau, Python, and TabPy transforms this visualization into an AI-powered predictive analytics dashboard.  Instead of merely describing historical data, the dashboard predicts expected CO₂ emissions and enables comparisons between actual and predicted values across different regions.  This approach provides valuable support for environmental planning, energy policy development, and sustainable decision-making.
• The successful integration of Tableau, Python, and TabPy transforms traditional data visualization into an AI-driven predictive analytics platform.  Rather than only describing historical data, the dashboard provides expected CO₂ emissions based on machine learning, enabling data-driven forecasting and more informed environmental decision-making.
• Business tax rates vary considerably across the world, emphasizing that tax policy is only one component of investment attractiveness. Strategic decisions should also consider complementary indicators such as GDP, Ease of Doing Business, political stability, infrastructure, labor availability, and market size.
• The analysis of the Top 10 and Bottom 10 countries by Business Tax Rate highlights substantial differences in taxation policies across the world. Countries with the highest business tax rates generally impose a heavier financial burden on businesses, which may limit private sector growth and reduce investment attractiveness if not accompanied by efficient public services and infrastructure.

Conversely, countries with lower business tax rates tend to create a more competitive business environment by encouraging entrepreneurship, attracting foreign direct investment, and supporting economic expansion. However, lower tax rates alone do not guarantee economic success, as sustainable growth also depends on political stability, regulatory quality, infrastructure, and workforce productivity.

Overall, the dashboard demonstrates that business taxation is a significant component of a country’s investment climate. A balanced tax policy that generates government revenue while maintaining business competitiveness is essential for long-term economic development.

Results & Recommendations:

• One of the most important observations from this dashboard is the absence of a strong inverse relationship between the two indicators.  If lower taxes alone created better business environments, countries with the lowest Business Tax Rates would consistently exhibit the highest Ease of Business scores.  However, the visualization indicates that this is not always the case.  Countries with relatively high tax rates may still achieve excellent Ease of Business scores because of:

-Efficient government services

-Simplified business regulations

-Strong legal systems

-Transparent administrative procedures

• Decision-makers seeking international expansion should prioritize The Americas, Asia, and Europe, as these regions account for more than 84% of the combined average GDP. Policymakers in lower-performing regions may use these findings to benchmark economic performance, attract investment, and design policies aimed at improving productivity and sustainable growth.  From a strategic perspective, the 40% Reference Line provides an effective decision-making benchmark. It enables analysts to distinguish between high-impact economies and those with relatively smaller contributions. Policymakers can use this threshold to identify the countries driving regional economic performance, while businesses can focus resources on markets that generate the greatest economic value.
• From a strategic perspective, the dashboard highlights significant demographic differences among countries. The United Arab Emirates and Qatar possess the highest proportions of working-age residents, making them attractive markets for labor-intensive industries and long-term investment. In contrast, Hong Kong SAR, South Korea, and Singapore are characterized by aging populations, requiring greater investment in healthcare infrastructure, pension sustainability, and policies to address future workforce shortages.
• The findings indicate that Iran’s health expenditure as a percentage of GDP increased from 4.6% in 2000 to 7.3% in 2010, reflecting a substantial rise in investment in the healthcare sector. However, this indicator gradually declined to 6.7% by 2012, suggesting the need to examine the economic and policy factors influencing this trend. Maintaining sustainable healthcare investment, improving the efficiency of health spending, preparing for the challenges of an aging population, and continuously monitoring key health indicators are essential strategies for enhancing the performance and long-term sustainability of Iran’s healthcare system.
• Increase investment in healthcare systems, particularly in regions with lower female life expectancy, such as Africa.  Strengthen maternal and child healthcare programs and expand preventive healthcare services.  Improve universal access to affordable and high-quality healthcare.  Learn from the successful healthcare policies implemented in high-performing regions such as the Americas, Europe, and Oceania.  Continuously monitor female life expectancy as a key indicator of healthcare performance and sustainable human development.
• Expand broadband Internet infrastructure to improve digital accessibility and support higher mobile technology adoption.  Increase investment in high-speed Internet networks (4G/5G and fiber-optic infrastructure) to accelerate digital transformation.  Promote affordable Internet access through supportive policies and competitive pricing to encourage greater mobile and Internet usage.  Prioritize digital inclusion initiatives in regions with low Internet penetration to reduce the digital divide.  Investigate outlier countries to identify factors influencing deviations from the overall trend and develop targeted digital strategies.  Integrate Internet and mobile development policies, as the strong relationship between these indicators suggests that improvements in Internet access can significantly enhance mobile technology adoption.  Monitor additional socioeconomic factors such as income level, education, urbanization, and telecommunications infrastructure to better explain the remaining variation in mobile phone usag.
• Increase investment in primary healthcare and maternal-child health services.  Improve the efficiency of healthcare spending through better resource allocation.  Expand vaccination, nutrition, and preventive healthcare programs.  Reduce regional inequalities in healthcare accessibility.  Monitor healthcare performance using data-driven indicators over time.  Strengthen public health infrastructure in developing regions.
• Countries classified in Cluster 4 should prioritize policies that increase international visitor arrivals to reduce tourism deficits and improve tourism balance.

Governments should invest in tourism infrastructure, transportation networks, and destination marketing to enhance international competitiveness and attract higher-value tourists.

Countries in Cluster 2 have stable tourism performance and can further strengthen their position by diversifying tourism products such as cultural, medical, eco-tourism, and business tourism.

Best practices from Clusters 1 and 3, which demonstrate strong positive tourism balances, should be studied and adapted by countries with lower tourism competitiveness.

Policymakers should continuously monitor inbound and outbound tourism trends to support evidence-based tourism planning and sustainable economic development.

Tourism balance should be considered as a strategic performance indicator alongside inbound and outbound tourism volumes when evaluating national tourism policies.

Countries experiencing high outbound tourism should encourage domestic tourism through investment in local attractions and promotional campaigns to retain tourism expenditure within the national economy.

Future analyses should incorporate additional variables such as GDP, tourism investment, visa policies, transportation accessibility, and tourism infrastructure to gain a more comprehensive understanding of international tourism competitiveness.

• Based on this analysis, policymakers should:

Invest in renewable energy sources to reduce dependence on fossil fuels.

Improve industrial energy efficiency through advanced technologies.

Promote clean transportation and electrification.

Encourage international cooperation for carbon reduction.

Support developing countries in adopting sustainable energy infrastructure.

• Increase the Share of Renewable Energy.  Since the predictive model indicates that higher energy consumption leads to higher CO₂ emissions, governments should increase investment in renewable energy sources such as solar, wind, and hydropower to reduce carbon intensity.  Improve Energy Efficiency:  Regions with steeper prediction lines should focus on improving industrial efficiency, adopting cleaner technologies, and reducing energy waste to lower carbon emissions.  Integrate Predictive Analytics into Environmental Planning.  Machine learning models can be incorporated into environmental decision-making processes to estimate future CO₂ emissions under different energy consumption scenarios before implementing major development projects.  Investigate Countries with Large Prediction Errors.  Countries whose actual emissions significantly exceed the predicted values should be further analyzed to identify inefficiencies, outdated technologies, or heavy dependence on fossil fuels.  Apply More Advanced Machine Learning Models.  Future studies can improve prediction accuracy by comparing Linear Regression with advanced algorithms such as:

Random Forest Regression

XGBoost

Gradient Boosting

Support Vector Regression (SVR)

Artificial Neural Networks

Include Additional Predictive Variables:  Future predictive models should incorporate additional socioeconomic and environmental indicators, including:

GDP

Population

Renewable Energy Consumption

Industrial Production

Urban Population

Transportation Indicators

Energy Intensity

to improve model performance.

• Perform Long-Term Forecasting:  Using a longer historical time series would enable forecasting CO₂ emissions for future years and support sustainable development planning.

Expand AI Integration in Business Intelligence Platforms:

The successful integration of Tableau, Python, and TabPy demonstrates that Business Intelligence platforms can be extended with Artificial Intelligence techniques. Organizations are encouraged to adopt AI-powered dashboards to enhance forecasting, decision-making, and environmental monitoring.

• Compare Business Tax Rate with the Ease of Business indicator to evaluate whether lower taxes actually improve the business environment.

Analyze tax rate trends over multiple years to identify changes in fiscal policies.

Compare GDP and Business Tax Rate to investigate the relationship between taxation and economic performance.

Identify countries with relatively low tax rates and strong economic output as potential investment destinations.

Combine this dashboard with indicators such as Days to Start Business and Population Total for a more comprehensive investment analysis.

• Governments with relatively high business tax rates should periodically evaluate their tax policies to ensure they remain competitive while maintaining sufficient public revenue.

Countries with low business tax rates should continue improving infrastructure, regulatory quality, and public services to maximize the benefits of their investment-friendly policies.

Business tax analysis should be combined with additional indicators such as GDP, Ease of Doing Business, Foreign Direct Investment (FDI), and Employment Rate to provide a more comprehensive assessment of a country’s economic competitiveness.

Policymakers should monitor changes in business tax rates over time to evaluate the effectiveness of fiscal reforms and their impact on investment and economic growth.

Future studies can expand this analysis by incorporating machine learning techniques to predict how changes in tax policies may influence investment, business performance, and economic development.

Action:

In this project, In this project, I used simple functions ,clauses, operations and query options to get my answers:

Operations:  Dual Axis, Reference Line, Sort, Format, Synchronize, Percentage, Trend Line, Pearson Correlation Coefficient, R2, P-Value, Page Shelf, Cluster, Filters, parameter, Longitude, Latitude.

Aggregate Functions:  SUM, AVERAGE.

Codes:  Corr, Window-SUM, SCRIPT_REAL, Regression, np.isnan, Sklearn.linear_model, model.predict.

Table Calculation:  Percent of total, Running total.

Charts:  Dual-axis, Pareto, lollipop, waterfall, Bar, Line.

Libraries:  Tabpy, numpy.

Link:

Thank you so much for reading my project.  I will be happy to receive your feedback and opinion about the project. If this project is useful for you, click on this link:

Link to project repository on GitHub