WITHDRAWN: Predictive and causal chain mining to discover actionable knowledge from stock markets

Abstract

Abstract In many scientific studies, discovering causal relationship is given high importance. Due to the availability of data in various domains, the research on mining causal relationships is growing steadily. Finding causal relationships from stock market datasets has its utility in that domain. Many researchers contributed towards developing algorithms for causal mining. In our prior work, we proposed algorithms for upstream and downstream causal relationships in stock market data. However, causal chain mining is relatively new research phenomenon where a set of inter-related actions are found and among the actions there exists causal relationship. Causal chains, in fact, reflect frequent occurrences of set of events with cause-effect relationship. In this paper we proposed a framework for mining causal relationships from stock market data. Two algorithms namely Stock Risk Prediction (SRP) and Causal Chain Miner (CCM) are proposed and implemented. An empirical study is made with a prototype application to validate the proposed framework. The experimental results showed the significance and usage of proposed causal chain mining and predictive algorithms which has comparable performance over the state of the art methods.