A multi-objective optimisation model for assignment of service to bank customers by using data mining and simulation

Recognising the customers' behavioural patterns, clustering and providing services to them were assumed as one of the most important issues of banks. In this research, five specifications of customers included last referral time, number of transaction, deposit amount, loan amount and balance of loans deferred values during one year was extracted from bank database and customers were clustered by k-means algorithm. Then, a multi-objective model of allocation of bank services to each one of clusters was designed. The purpose of designed model was increasing the customers' satisfactions, cost reduction and risk reduction of services allocation. As this problem showed no optimum solution and each one of specifications of customers has a probability distribution function, the simulation was used for solving. To determine the solution close to the optimum value, annealing algorithm was used for making neighbour solutions and implementation model was implemented. The results showed significant improvement comparing to current status. In this study, Weka and R software was used for data mining, and arena software for optimisation and simulation.