Fragment Based Approach to Forecast Association Rules from Indian IT Stock Transaction Data

In this research we mainly focus on overcoming the drawbacks in FITI approach in predicting the stock market and propose a new approach called fragment based mining which gives some promising results as compared to FITI. FITI consists of all the transaction from the stock market some of which are not necessary and simply increases the overhead in processing the data, so we improve this by reducing the number of transactions using some aggregate functions, so the time needed to process the transactions will be less and generate some efficient rules from which we predict the stock market behavior. This research is purely based on the data mining technique called association mining. Association rules suites the behavior of stock market and helps in analyzing the associations among the companies. As mentioned above we propose a technique Fragment Based mining which helps in minimizing the input transaction table size which leads to reduced processing time. Keywords— FITI; Fragment Based Mining, Association mining; Stock Data.