An application of DATALOGIC/R knowledge discovery tool to identify strong predictive rules in stock market data

摘要: An application of a methodology for discovering strong probabilistic rules in data is presented. The based on an extended model rough sets called variable precision incorporated DATALOGIC/R knowledge discovery tool from Reduct Systems Inc. It has been applied to analyze monthly stock market collected over ten year period. objective the analysis was identify dominant relationships among fluctuations indicators and prices. For purpose comparison, both precise imprecise, weak were discovered evaluated by domain expert, broker. evaluation revealed that (supported many cases) essentially confirm expert's experiences whereas are often difficult interpret. This suggests use rule strength as primary criteria selection potentially useful predictive rules.