One of the most challenging problems in the Stock Market is predicting how stocks will perform in the future. There are many different factors that affect share prices, and so predicting their movement with high accuracy is difficult.
In addition to the large number of unknown factors, a lot of noise is inherent in the data as well. Therefore, different samples of data from various timeframes need to be analyzed to conclusively evaluate the effectiveness of any particular quantitative methodology.
This paper will be looking at a few different statistical and learning methods applied to this problem and attempt to benchmark their performance against real-world data. Each of the techniques described was implemented in Python using statistical library tools.
For a more thorough explanation, please see the Results and Methodology.pdf file