Phase-3

GDP Growth Prediction Project

This project focuses on predicting annual GDP growth using machine learning models based on exchange rates, inflation rates, and historical GDP data.

Table of Contents

• Introduction
• Business Understanding
• Problem Statement
• Data Understanding
• Data Preparation
• Feature Engineering
• Exploratory Data Analysis
• Data Modeling
• Model Evaluation
• Ensemble Methods
• Conclusions
• Recommendations
• Installation
• Contributing

Introduction

This project aims to predict annual GDP growth by leveraging machine learning techniques and analyzing the relationships between exchange rates, inflation rates, and historical GDP data.

Business Understanding

Understanding and predicting GDP growth is essential for policymakers, economists, and businesses. Accurate predictions can guide economic policies, investment decisions, and risk management strategies.

Problem Statement

The main objective is to develop machine learning models that accurately predict annual GDP growth based on exchange rates, inflation rates, and historical GDP data.

Data Understanding

The dataset comprises three main sources of information: Key CBK Indicative Exchange Rates, Inflation Rates, and Annual GDP data. These datasets provide valuable insights into the economic landscape and its potential impact on GDP growth.

Data Preparation

Data from the three sources are merged and preprocessed to create a comprehensive dataset for analysis and modeling.

Feature Engineering

New features are created based on domain knowledge and data transformation to enhance the models' predictive capabilities.

Exploratory Data Analysis

Univariate, bivariate, and multivariate analyses are performed to gain insights into the relationships between variables. Visualizations aid in understanding data patterns.

Data Modeling

Machine learning models, including Random Forest Regressor and HistGradientBoostingRegressor, are trained to predict annual GDP growth based on the selected features.

Model Evaluation

Model performance is evaluated using metrics such as Root Mean Squared Error (RMSE) and R-squared (R2) score. These metrics provide insights into the accuracy and explanatory power of the models.

Ensemble Methods

Ensemble methods like Random Forest and HistGradientBoosting are used to combine the predictions of multiple models, enhancing overall predictive accuracy.

Conclusions

The project's findings highlight the importance of exchange rates, inflation rates, and historical GDP data in predicting annual GDP growth. The models demonstrate strong predictive power and can offer valuable insights for economic decision-making.

Recommendations

Based on the analysis, recommendations are provided for currency exchange rate monitoring, inflation rate management, and leveraging historical data for informed decision-making.

Usage

Programming Language and Dependencies

This project is written in Python and requires the following packages:

• pandas
• numpy
• matplotlib
• scikit-learn

Running the Code

1. Clone this repository to your local machine.
2. Install the required packages using pip install -r requirements.txt.
3. Preprocess the data by running data_preparation.ipynb.
4. Perform feature engineering and exploratory data analysis using feature_engineering.ipynb and exploratory_data_analysis.ipynb.
5. Train and evaluate machine learning models with data_modeling.ipynb.
6. Run ensemble_methods.ipynb to implement ensemble methods.
7. Review conclusions and recommendations in conclusions.ipynb. some of this will be added later

Installation

List any specific installation requirements, dependencies, or packages needed to run the code successfully.

Contributing

Clone our github repository😉