Skip to content

Stock Price prediction using news data. The datasets used consists news and stock price data from 2008 to 2016. The polarity(Subjectivity, Objectivity, Positive, Negative, Neutral) data is gathered from the news data and further used to predict stock prices. Achieved an accuracy of 94% using XGBoost.

Notifications You must be signed in to change notification settings

ahmedyes2000/Stock-Price-Prediction-Model

 
 

Repository files navigation

Stock-Price-Prediction-Model

Kindly refer to the StockPredictionModelv3.ipynb file for the detailed explaination and results

Stock Market Price Prediction with New Data

Breif Overview:

The model created below is for prediction the stock prices of a Company.

There are two datasets Stock Prices Dataset for Dow Jones Inc Top 25 headlines for everyday for the past 8 years

The notebook is briefly summarized as follows:

Data Preparation - Preparing data for evaluation.

Data Quality Checks - Performing basic checks on data for better understanding of data.

Feature inspection and filtering - Correlation and feature Mutual information plots against the target variable. Inspection of the Binary, categorical and other variables.

Feature importance ranking via learning models

Training - training data against multiple machine learning algorthms and fine tuning a couple of algorithms for accuracy

About

Stock Price prediction using news data. The datasets used consists news and stock price data from 2008 to 2016. The polarity(Subjectivity, Objectivity, Positive, Negative, Neutral) data is gathered from the news data and further used to predict stock prices. Achieved an accuracy of 94% using XGBoost.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 89.3%
  • HTML 10.0%
  • Python 0.7%