A Data Science project using Python in order to predict whether an equity in the IT sector has a positive growth or a negative growth. This project came into existence in order to gauge prevailing technical trading strategies on a large amount of historical data to determine the best performer. Performance is to be judged on the magnitude of return and consistency. The results can be used to build a statistically trained model that optimizes the chosen strategy's parameters for a selected trading period. The trading period can be defined as the time from entry (purchase of underlying security) to exit (sale of underlying security).
Structure of executing this project:
- Create a folder called "data" in a location on your computer
- Place the StockSymbols_All file in the data folder
- Execute the Technical_indicators script
- This script will take a while to complete execution
- Notice that equities_IT_TS folder gets created which contains a preprocessed and a processed folder with the CSVs of each equity
- Place the merge_All_CSV script in both the preprocessed and processed folders and execute them individually (Change the name of the Final CSV to whatever you desire. Currently it is main.csv)
- Notice that a new csv with all the csv data is created
- Use this CSV as your dataset
- Execute the quantitative_finance script and make necessary changes
Note: Find the poster depicting the performance comparison between the various models fitted on the dataset