Screener

Screener is a Python-based tool designed for analyzing the S&P 500 stocks. It calculates various financial metrics such as expected returns, standard deviation, variance, and covariance, and identifies optimal portfolio weights for minimum variance portfolios (MVP). The project leverages historical data, performs financial analysis, and saves results in structured CSV files for further examination and use.

Project Structure

The project is divided into several sequential steps, each focusing on a specific aspect of stock analysis. The following is a list of the main files and their functions:

1. Download SP500 symbols and their historical data

   • Download historical stock data for S&P 500 symbols.
   • Save the historical data for each stock.

2. Calculate Expected Return, Standard Deviation, and Variance for each stock

   • Compute the expected return, standard deviation, and variance for each stock based on historical data.
   • Filter stocks with positive expected returns and save the metrics in a DataFrame.
   • Save the results to sp500_stock_metrics.csv.

3. Analyze Positive Expected Return Stocks

   • Load the sp500_stock_metrics.csv dataset.
   • Filter stocks where the expected return is greater than variance.
   • Add a 'Comparison' column to represent the difference between expected return and variance.
   • Save the filtered dataset to filtered_positive_returns.csv.

4. Optimal Portfolio Candidates Analysis

   • Load optimal_portfolio_candidates.csv.
   • Download historical stock data for selected tickers.
   • Calculate the percentage returns and expected returns for each stock.
   • Calculate the covariance between each pair of stocks and display the covariance matrix.
   • Save the covariance matrix to covariance_matrix.csv.

5. Minimum Variance Portfolio Calculation

   • Load optimal_portfolio_candidates.csv and historical data using yfinance.
   • Calculate expected returns and covariance matrix for each stock.
   • Instantiate the Efficient Frontier class with the calculated expected returns and covariance matrix.
   • Determine the Minimum Variance Portfolio (MVP).
   • Save MVP info and optimal weights to mvp_weights.csv and mvp_info.csv.

6. Final Consolidation

   • Consolidate all results, including metrics and MVP information, into a single CSV file for easy access and analysis.

Getting Started

To run this project, you will need Python 3 and the following packages:

• yfinance
• pandas
• numpy
• cvxpy
• matplotlib (for visualizations if needed)

Installation

To install dependencies, run:

pip install yfinance pandas numpy cvxpy matplotlib