This research involves implementation of genetic network programming (GNP) and ant colony optimization (ACO) to solve the sequential rule mining problem for commercial recommendations in time-related transaction databases. Excellent recommender systems should be capable of detecting the customers’ preference in a proactive and efficient manner, which requires exploring customers’ potential needs with an accurate and timely approach. Due to the changing nature of customers’ preferences and the differences with the traditional find-all-then-prune approach, the interesting temporal association rules are extracted by the metaheuristics, genetic algorithms-based method of GNP. Additionally, a useful model is constructed using the obtained rules to forecast future customer needs and an ACO approach to evolve the online recommender system continuously. The methodology is experimentally evaluated in a real-world application by analysing the customer database of an online supermarket.

As a new travel model, the bike-sharing system (BSS) solves the ‘last kilometer’ problem and has developed rapidly for its convenience. However, many accompanying problems have emerged. In China, parking violation problems—such as severe traffic congestion—are caused by dock-less shared bikes. Furthermore, a large number of shared bikes have to be scrapped early for vandalism. As a special form of public good, bike-sharing also faces the dilemma of negative externalities. Seeking a solution, Mobike has conducted a credit supervision mechanism, which transfers the users’ different behavior to credits for user behavior regulation, but with unsatisfactory results. The goal of the paper is to test the validity of credit supervision mechanism from user’s perspective to regulate the abuse of sharing bike by simulating the use scenario of BSS in real life in a lab experiment based on induced value theory. The behavioral and pre- and post-experiment survey data were thoroughly analyzed. The results show that, within a negative context, the credit supervision system has a more significant effect on inducing proper user behavior, which improves after adding a real-time feedback mechanism. Finally, we provide effective suggestions to policy makers and shared bike companies for inducing positive user behavior.