A Real Data-Driven Analytical Model to Predict Information Technology Sector Index Price of S&P 500

TL;DR

This paper develops a data-driven nonlinear model to accurately predict the weekly closing price of the S&P 500 Information Technology Sector Index using financial and economic indicators, highlighting its high predictive accuracy.

Contribution

It introduces a novel nonlinear analytical model that incorporates multiple indicators and their interactions to predict sector index prices with high accuracy.

Findings

Model achieves 99.4% predictive accuracy.

Significant indicators and interactions identified for stock return prediction.

Model demonstrates practical usefulness for investors and analysts.

Abstract

S&P 500 Index is one of the most sought after stock indices in the world. In particular, Information Technology Sector of S&P 500 is the number one business segment of the S&P 500 in terms of market capital, annual revenue and the number of companies (75) associated with it, and is one of the most attracting areas for many investors due to high percentage annual returns on investment over the years. A non-linear real data-driven analytical model is built to predict the Weekly Closing Price (WCP) of the Information Technology Sector Index of S&P 500 using six financial, four economic indicators and their two way interactions as the attributable entities that drive the stock returns. We rank the statistically significant indicators and their interactions based on the percentage of contribution to the $WCP$ of the Information Technology Sector Index of the S&P 500 that provides significant information for the beneficiary of the proposed predictive model. The model has the predictive accuracy of 99.4%, and the paper presents some intriguing findings and the model's usefulness.