Contrasting Approaches for Forecasting the S&P 500 Index

Merrill Warkentin (Editor), The Best Thinking in Business Analytics, Pearson Financial Times Press Analytics, 2015, Forthcoming

Posted: 30 Apr 2015

Date Written: April 28, 2015

Abstract

This paper develops and compares several methods of forecasting the S&P 500 Index using only data based on the closing value and trained over a six-decade data set. The methodologies include a C5.0 decision tree, a neural network, and a group of forecasts based on training set patterns of directional change from one to seven days in length. Methods are compared by using the number of correct forecast directions, and by calculating the amount of gain/loss. We find that the neural network yielded the most gain, but the six-day string pattern did best predicting that the Index would move up.

Keywords: S&P 500 Index, Forecasting Approaches, Decision Tree, Neural Networks

JEL Classification: C5, C18, G1

Suggested Citation

Malliaris, A. (Tassos) G. and Malliaris, Mary, Contrasting Approaches for Forecasting the S&P 500 Index (April 28, 2015). Merrill Warkentin (Editor), The Best Thinking in Business Analytics, Pearson Financial Times Press Analytics, 2015, Forthcoming , Available at SSRN: https://ssrn.com/abstract=2600211

A. (Tassos) G. Malliaris (Contact Author)

Loyola University Chicago ( email )

16 E. Pearson Ave
Quinlan School of Business
Chicago, IL 60611
United States
312-915-6063 (Phone)

Mary Malliaris

Loyola University Chicago ( email )

16 East Pearson Street
Chicago, IL 60611
United States
312-915-7064 (Phone)

Do you have negative results from your research you’d like to share?

Paper statistics

Abstract Views
458
PlumX Metrics