This project aims to predict the performance of various sectors compared to the Nifty 50 benchmark index using econometric and machine learning models based on global and local economic variables.
- The project starts by gathering historical data for various Nifty sector indices and relevant macroeconomic variables.
- Collected data on key macroeconomic variables such as GDP, CPI, interest rates, and unemployment from sources like the World Bank, Indian Fama-French Momentum, and Macrotrends.
- EDA is performed to understand the data and identify potential correlations.
- Visualize the data using libraries like
matplotlib
andseaborn
. - Predictive models are built and trained on historical data to forecast sector performance.
- Utilize econometric models like ARIMA or machine learning models such as Random Forest, XGBoost, etc.
- Model performance is evaluated using statistical metrics, and the results are compiled into a comprehensive report.
- Python 3.x
- Necessary Python libraries:
yfinance
,pandas
,numpy
,matplotlib
,seaborn
,statsmodels
,scikit-learn
-
Clone the repository:
git clone https://github.com/your-username/sector-analysis-portfolio.git cd sector-analysis-portfolio
-
Install the required libraries:
pip install -r requirements.txt
-
Open the notebook and run the cells.