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

13 Pages Posted: 2 Jan 2016

See all articles by Tamal Datta Chaudhuri

Tamal Datta Chaudhuri

Calcutta Business School

Indranil Ghosh

Calcutta Business School

Shahira Eram

Calcutta Business School

Date Written: December 2015

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

Suggested Citation

Datta Chaudhuri, Tamal and Ghosh, Indranil and Eram, Shahira, Predicting Stock Returns of Mid Cap Firms in India – An Application of Random Forest and Dynamic Evolving Neural Fuzzy Inference System (December 2015). Available at SSRN: https://ssrn.com/abstract=2709913 or http://dx.doi.org/10.2139/ssrn.2709913

Tamal Datta Chaudhuri

Calcutta Business School ( email )

Diamond Harbor Road, Bishnupur
24 Paraganas, West Bengal 743503
India
9831054204 (Phone)

Indranil Ghosh (Contact Author)

Calcutta Business School ( email )

Bishnupur
South 24 Parganas
Kolkata, West Bengal 743503
India

Shahira Eram

Calcutta Business School ( email )

Bishnupur
South 24 Parganas
Kolkata, West Bengal 743503
India

Register to save articles to
your library

Register

Paper statistics

Downloads
131
rank
208,902
Abstract Views
589
PlumX Metrics