A new fuzzy rule-based optimization approach for predicting the user behaviour classification in M-commerce

• Published in: International journal of reconfigurable and embedded systems Vol. 12; no. 3; p. 320
• Main Authors: Ramaraj, Muniappan, Chembath, Jothish, Adishankar Nithya, Balluru Thammaiahshetty, Ganesan, Gnanakumar, Uma Shankari, Balakrishnan, Karthikeyan, Nagarajan
• Format: Journal Article
• Language: English
• Published: Yogyakarta IAES Institute of Advanced Engineering and Science 01.11.2023
• Subjects: Body weight; Cellular telephones; Classification; Computer science; Data banks; Data mining; Embedded systems; Enterprise search; Genetic algorithms; Genomes; Optimization; Pattern recognition; Predictions; Shopping; Smartphones; Social networks; User behavior
• ISSN: 2089-4864; 2722-2608; 2089-4864
• DOI: 10.11591/ijres.v12.i3.pp320-328

A novel approach for classification of user behaviour prediction using proposed embracing the optimized fuzzy techniques to predicting the user data in M-commerce. Using this technique, network users can be monitored and their behavior categorized according to their activity. Unauthorized use of the website, network security breach attempts, firewalls, unauthorized access to the service and frequency of attempts. The proposed method has been adapted with the user classification to predict the predefine segregation of information to extract from user logs. Pattern recognition is a method for information discovery that results in current information patterns. Continuing items are a required task in various knowledge mining operations in pursuit of fascinating types from the data banks, including association rules, connections, sequences, episodes, classifications, bunches and much more. The functionality findings achieved in relation to precision and recall show that our technique can contribute to predicting more accurately than the different approaches. This paper focuses on to enhance the far better forecast for the mobile phone users through locating more reliable frequent patterns coming from the consumer deal data bank through looking at the body weight value of each thing collection and also examining the consumer activities on all time intervals.