MODIFIED DECISION TABLE CLASSIFIER BY USING DECISION SUPPORT AND CONFIDENCE IN ONLINE SHOPPING DATASET

Online shopping has a shopping channel for purchasing various items through online medium. The main problem is social CRM mining is to extract different information from the previous records so that decision can be made for further planning of the business. The major issue in social data mining due to changes in the trends of the products and different buyers various sales in the market gets affected. Decision table classifier divides the data into different tables that selects various attributes that plays major role for development of different decisions about online shopping. Decision table classifier has been enhanced for computation of support and confidence value of the basis of testing and training dataset. After labelling to all the instances available in the dataset performance evaluation parameters have been computed. On the basis of these label performance evaluation parameters have been computed. By these performance evaluation parameters, that proposed approach provides better results than decision table classifier, conjunctive classifier and J-rip classifier.