Beyond Fundamentals Or Technicals: Unveiling Synergies Through Linear And Non-Linear Models For Stock Index Predcition

Abstract

Stock market prediction is a debatable area of research since many decades and various studies have been done to predict the returns and movement of stock prices which will help the investors to take long or short positions in their portfolio. The main objective of the study is to understand the efficacy of fundamental, technical indicators and combined (technical and fundamental) in prediction of CNX Nifty 50 Index employing Linear regression, Random forests, Decision trees, Support Vector regression and Feed forward neural networks. Required data for analysis are collected from NSE website and time frame of the data collected is from 01-Jan-2018 to 31-Dec-2021. It was found from the analysis that feed neural networks outperform other models and linear model also provide equally good results with technical indicators and hybrid indicators. Even though technical analysis and combined approach have good performance metrics, combined approach has lower error metrics such as MAD and SSR than technical analysis