Predicting Stock Returns of Mid Cap Firms in India – An Application of Random Forest and Dynamic Evolving Neural Fuzzy Inference System

Abstract

The paper examines the pattern of stock returns of mid cap Indian companies over a period of time and proposes frameworks for predictive modelling. Ten features are identified as predictors of stock returns. Subsequently two Machine Learning models, Random Forest and Dynamic Neural Fuzzy Inference System have been employed to check whether the returns can be predicted or not. Experimental setups have been designed and predictive accuracy of the respective models are evaluated using some standard measures. Further, investigation has also been made to recognize the key influential predictors by assessing their impact applying Genetic Algorithm. Our findings suggest that the returns of stocks of mid cap organizations in India can efficiently be forecasted using the frameworks discussed.

Keywords: Stock returns, Machine Learning, Random Forest, Dynamic Neural Fuzzy Inference System, Genetic Algorithm

JEL Classification: C45, C53, G11