Fuzzy Logic and Machine Learning Hybrid Model for Influencing Consumer Purchasing Behavior in E-Commerce

With the rise of the Internet, online shopping has become an integral aspect of contemporary living, greatly impacting consumer behaviour in e-commerce. In e-commerce, good emotions and easy navigation play significant roles in driving consumer actions, in contrast to traditional retail settings were establishing human rapport influences purchasing decisions. The suggested approach employs state-of-the-art data preparation methods, such as handling missing values, encoding categorical variables, and scaling features to improve data quality, in order to comprehend and foretell these behaviours. First, the FKNN technique is used for regression modelling after using SA for effective feature selection. In an effort to enhance prediction accuracy, this study explores various FKNN versions based on Minkowski, Manhattan, and Euclidean distances. By obtaining the best prediction accuracy, the lowest average error, and an overall accuracy of 95.36%, the results show that the MdFKNN far surpasses previous methods. The MdFKNN model shows promise in solving regression issues in e-commerce analytics, as shown by these results. Ultimately, the study highlights how important intelligent modelling techniques are for better understanding consumer purchase behaviour in e-commerce environments and making predictions.