A predictive analytics framework for opportunity sensing in stock market
10.48129/kjs.splml.18993
DOI:
https://doi.org/10.48129/kjs.splml.18993Abstract
Large volume, random fluctuations and distractive patterns in raw price data lead to overfitting in stock price prediction. Thus research papers in this area suffer from multiple limitations: Very short prediction period from one day to one week, consideration of few stocks only instead of whole of stock market spectrum, exploration of more suitable machine learning algorithms. By overcoming the problems of raw data these limitations can be conquered. Proposed work uses a supervised machine learning approach on statistically learned macrofeatures obtained from gist of input data, free from raw data drawbacks, to predict the price band for the upcoming month and a half for almost all NIFTY50 stocks. The predicted bands are tested for precision in comparison with actual stock price bands. Motivating outcomes so obtained were used to sense opportunity for buying / selling / wait. The results showed that the proposed strategy is quite effective and can be successfully monetized.