A Stock Trading Intention Recognition Model Based on Data Clustering

摘要

In practice, many physics principles have been employed to derive various models of stock transaction behavior analysis. However, few studies have been done on the stock trading intention recognition based on feature selection and match on time series stock transaction data. The purpose of this paper is to show how to discover the real stock trading intention by analyzing historical transaction data. Therefore, the proposed recognition model utilizes data clustering with feature selection, trace constructing and pattern matching together to fulfill intention mining and recognizing. The experiment results show the better performance.