Abstract

Bayesian network is the graphical model which can represent the stochastic dependency of the random variables via the acyclic directed graph. In this study, Bayesian network is applied for the up/down analysis of the stock index. The up/down rates of the daily stock indexes in three major markets are taken as the network nodes and then, the network is determined by K2 algorithm with the K2 metric as the prediction accuracy of the network. The present algorithm is applied for predicting the up/down analysis of the daily stock indeies in 2007 and the results are compared with the traditional algorithms; Psychological line and trend estimation, which are popular algorithms which are well-known by the traders. Their accuracy comparison shows that the average correction rate of the present algorithm is almost 60%, which is almost equal or higher than them of the traditional algorithms such as the psychological line (50-59%) and the trend estimation (50-52%). Moreover, the vertical trading results reveal that the profit of the present algorithm is much greater than the others.

This work is licensed under a Creative Commons Attribution 4.0 License.