Skip to content

Latest commit

 

History

History
23 lines (12 loc) · 800 Bytes

README.md

File metadata and controls

23 lines (12 loc) · 800 Bytes

Stock Market Prediction using Numerical and Textual Analysis

A brief description of what this project does and who it's for

Objective

To Create a hybrid model for stock price or performance prediction using numerical analysis of historical stock prices, and sentiment analysis of news headlines

Approach

Extract the Sentiment Scores from the news headlines data using the SentimentIntensityAnalyzer.

Try different Regression Models on the merged dataset for the best accuracy.

Applied RandomForestRegressor, DecisionTreeRegressor and XGBRegressor.

Achieved a Mean Squared Error of 0.0346(Best outcome) from the DecisionTreeRegressor.

Datasets used

News Headlines Data from https://bit.ly/36fFPI6

Historical stock prices(SENSEX (S&P BSE SENSEX)) from https://finance.yahoo.com/