A Data-Integrated Tree-Based Simulation to Predict Financial Market Movement

The Standard and Poor’s 500 Index (S&P500) is one of the commonly used indices on the New York Stock Exchange. The 500 publicly traded companies that make up the index are chosen by a committee to best reflect the overall market of the United States. The broader objective of this research is to estimate the dynamics of the financial market movement in the United States. It is achieved by developing a data-integrated tree-based simulation model to predict S&P500 open and close values for a week. Classification and Regression Trees (CART) a data mining method is utilized to extract patterns of the financial market dynamics based on a data set collected from May 1, 2008 to November 30, 2009. The data set included the daily movement of financial markets in seven countries in Asia and Europe in relation to the daily movement of the S&P500. CART also utilized data on the currency exchange rates to capture the financial dynamics between the US and other countries. The simulation model repeatedly samples from four trees developed by CART to know how the opening and closing values of the S&P500 move in tandem with the other markets. DOI: 10.4018/joris.2012070105 International Journal of Operations Research and Information Systems, 3(3), 74-86, July-September 2012 75 Copyright © 2012, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited. One of the primary tasks of institutional fund managers and financial analysts is to predict how the market is going to move on a daily basis so that they can better reach their returns goals. To aid the fund managers and financial analysts, this research develops a data-integrated tree-based simulation model to predict how the opening and closing price of the S&P500 move in tandem with the other markets. Classification and Regression Tree (CART) model – a data mining tool for prediction and classification (Breiman, Friedman, Oishen, & Stone, 1984)is used to develop four regression tree structures: (1) “first” tree predicts S&P500 Open value for Monday mornings based on other market indices, currency exchange rates, and S&P500 open and close values of the prior Friday; (2) “second” tree predicts the S&P500 close value for Monday evenings based on other market indices, currency exchange rates, S&P500 open and close values of the prior Friday, and the predicted S&P500 open value for that morning; (3) “third” tree predicts the S&P500 open values for Tuesday through Friday based on previous day’s predicted S&P500 open and close values; and (4) “fourth” tree predicts the S&P500 close values for Tuesday through Friday based on the predicted value of that day’s S&P500 open value, and previous day’s open and close values. Simulation models developed by sampling from these four trees are better representation of the actual system and more efficient to execute.