kedarghule/Stock-Portfolio-Diversification-Using-Clustering-and-Volatility-Prediction

The project aims to profile stocks with similar weekly percentage returns using K-Means Clustering. The project calculates realized volatility for each stock and predicts realized volatility for each stock using classical volatility models and machine learning models and comparing their performance. This is a capstone project for CIVE 7100 Time Series and Geospatial Data Sciences.

27
/ 100
Experimental

This project helps investors diversify their stock portfolio by identifying stocks with similar weekly return patterns and predicting their future volatility. It takes historical stock data from the S&P 500 and provides clusters of similar stocks along with volatility forecasts. Individual investors looking to make informed decisions about their stock holdings would find this useful.

No commits in the last 6 months.

Use this if you are an investor seeking to build a more resilient and diversified stock portfolio by understanding stock volatility and grouping similar assets.

Not ideal if you are looking for direct stock price predictions or a tool for high-frequency trading.

personal-investing portfolio-diversification stock-analysis financial-risk-management
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

12

Forks

3

Language

Jupyter Notebook

License

Last pushed

Oct 30, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kedarghule/Stock-Portfolio-Diversification-Using-Clustering-and-Volatility-Prediction"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.