Stock Market Price Predictor using Supervised Learning

Aim

To examine a number of different forecasting techniques to predict future stock returns based on past returns and numerical news indicators to construct a portfolio of multiple stocks in order to diversify the risk. We do this by applying supervised learning methods for stock price forecasting by interpreting the seemingly chaotic market data.

Setup Instructions

    $ workon myvirtualenv                                  [Optional]
    $ pip install -r requirements.txt
    $ python scripts/Algorithms/regression_models.py <input-dir> <output-dir>

Download the Dataset needed for running the code from here.

Project Concept Video

Methodology

1. Preprocessing and Cleaning
2. Feature Extraction
3. Twitter Sentiment Analysis and Score
4. Data Normalization
5. Analysis of various supervised learning methods
6. Conclusions

Research Paper

• Machine Learning in Stock Price Trend Forecasting. Yuqing Dai, Yuning Zhang
• Stock Market Forecasting Using Machine Learning Algorithms. Shunrong Shen, Haomiao Jiang. Department of Electrical Engineering. Stanford University
• How can machine learning help stock investment?, Xin Guo

Datasets used

1. http://www.nasdaq.com/
2. https://in.finance.yahoo.com
3. https://www.google.com/finance

Useful Links

• Slides: http://www.slideshare.net/SharvilKatariya/stock-price-trend-forecasting-using-supervised-learning
• Video: https://www.youtube.com/watch?v=z6U0OKGrhy0
• Report: https://github.com/scorpionhiccup/StockPricePrediction/blob/master/Report.pdf

References

• Recurrent Neural Networks - LSTM Models
• ARIMA Models
• https://github.com/dv-lebedev/google-quote-downloader
• Book Value
• http://www.investopedia.com/articles/basics/09/simplified-measuring-interpreting-volatility.asp
• Volatility
• https://github.com/dzitkowskik/StockPredictionRNN
• Scikit-Learn
• Theano