Neural Network vs. Cycle Analysis to Predict the Stock Market

The stock market can be presented by S&P-500 index. It is possible to build its different statistical forecasts using historical data. The purpose of the research was to compare two statistical methods: one that based on Cycle Analysis, another - on Neural Network. We used price and volume data to train this particular Neural Network.

A picture below shows how actual 5-day performance (yellow line) differ from predicted performances by these two methods. The top half is the comparison of Neural Network prediction, bottom half - Cycle Analysis. Green bars mean buy signals, red - sell.

Three major conclusions:

1. Cycle Analysis prediction gives signals too early, Neural Network prediction - too late.
   
2. In average, Cycle Analysis prediction showed slightly better accuracy than Neural Network prediction for the last six months (from June 2009 to January 2010).
   
3. It it possible to get a superior prediction by combining these two methods.
   

© Alex Shmatov. Published with permission of the copyright owner. Further reproduction strictly prohibited without permission.