Skip to content

tooshiNoko/Global-Economy-Indicators-Research-Study

Repository files navigation

Data Analytics Bootcamp Final Project

Global Economy Indicators Study and Forecast Predictor

Welcome to the Global Economy Indicators Study and Forecast Predictor repository. This project focuses on providing comprehensive insights and predictive analytics for global economic indicators using forecasting techniques.

1. Data Loading

Coding language

python

  • Main Libraries:

    • numpy
    • pandas
  • Data Visualization:

    • matplotlib.pyplot
    • seaborn
    • plotly.express
    • plotly.graph_objects
  • Statistical Testing:

    • scipy
  • Time Series Analysis:

    • statsmodels
    • pmdarima
    • neuralprophet
    • sklearn

2. Role of EU Analysts

  • As EU analysts, our objective is to analyze economic indicators, compare them with major world powers, and predict Eurozone GDP. This involves:

    • Gathering and processing economic data from various sources.
    • Visualizing and interpreting data trends using Power BI and Streamlit applications.
    • Implementing predictive models such as ARIMA, NeuralProphet, and Voting Ensemble to forecast economic variables.
    • Creating insights and reports to support decision-making within the European Union.

3. Power BI and Streamlit Applications

  • Power BI Dashboard:

    • Power BI
      • Developed a dashboard to visualize and report major global economic indicators, comparing them with major world powers and the Eurozone.
      • Explore Power BI Dashboard
  • Streamlit Application:

    • Streamlit
      • Integration of Azure ML for real-time GDP predictions
      • Check the Streamlit app!

4. Model Comparisons

  • Predictive Models Used:

    • ARIMA
      • Implemented ARIMA model for time series forecasting in Jupyter Notebook.
    • NeuralProphet
      • Utilized NeuralProphet for advanced time series forecasting in Jupyter Notebook.
    • Voting Ensemble
      • A Voting Ensemble model developed using Auto Machine Learning has been implemented in Azure for forecasting.
  • Comparative Analysis:

    • Conducted a comparative analysis of the predictive performance of ARIMA, NeuralProphet, and Voting Ensemble models.
    • Evaluated accuracy, robustness, and computational efficiency across different economic indicators.

5. Contributors

Special thanks to all contributors who have made this project possible through their dedication and expertise.


Explore the future of global economic forecasting with us using advanced analytics and comprehensive data insights. For further details, refer to our documentation and interactive applications on Power BI and Streamlit.

Let's predict the future of global economies together! 🌍💡

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published