Trend discovery in financial time series data using a case based fuzzy decision tree

摘要: Research highlights? A novel case based fuzzy decision tree model is developed to predict the time series behavior in future. ? Fuzzy generated from stock database can be further applied predicting price's movement. Experimental results for test data S&P500 and stocks show convincing results. In recent years, many attempts have been of However, these could not build an accurate efficient trading system owing high dimensionality non-stationary variations price within a large historic database. To solve this problem, paper applies logic as mining process generate trees containing historical information. There are attributes often it impossible develop mathematical classify data. This establishes identify most important attributes, extract set rules that used The then converted decision-making movement on its current condition. demonstrate effectiveness CBFDT model, experimentally compared with other approaches Standard & Poor's 500 (S&P500) index some S&P500. overall performances very thus provides new implication research dealing financial