Abstract One of the major challenges in the banking sector is cash-in-transit (CIT), which involves moving cash and valuables securely from one location to another. Banks and other financial institutions rely on CIT services to protect their cash operations. These operations require the transportation of banknotes, coins, and other items of value. The main risks associated with CIT are routing plans and human factors, such as the possibility of collusion between staff and robbers or the formation of habits that make transfers predictable. In order to address these risks, we propose a multi-objective mathematical model that designs random schedules. The first objective function seeks to minimize the similarity of schedules among the staff, to avoid creating regular patterns. The second objective function tries to reduce travel time and the time spent by the staff inside the vehicle, to lower the chances of fatigue or distraction. The third objective function intends to minimize exposure to theft by considering the amount of money transferred and the travel duration. The proposed CIT problem is very complex and hard to solve, as it belongs to the NP-hard class of problems. Therefore, we develop a hybrid algorithm, called MOPGA, that combines NSGA II and MOPSO algorithms. We compare the proposed algorithm with NSGA-II, PESA, MOEA/D, and SPEA on several test instances. The results show that it delivers superior solution quality with competitive computational time, confirming its effectiveness for solving the CIT problem.

Abstract Nowadays, fierce competition enforces supply chain planners to develop market‐oriented production strategies. Customer order decoupling point (CODP) could increase the supply chain efficiency and responsiveness simultaneously. The right position of CODP in production industries will result in a pattern for trade‐off between responsiveness and operational efficiency. The purpose of this paper is to address the positioning problem of a push‐pull boundary in a fuzzy hesitant environment. To this end, a hybrid multi‐criteria decision‐making methodology of analytic network process (ANP) and VIKOR is proposed in a hesitant judgement environment to determine the position of CODP in a supply chain. Finally, CODP positioning in the apparel supply chain, as an industry‐based example, is analysed to show the applicability of the proposed method.

We propose an adaptive neuro-fuzzy inference system (ANFIS) for stock portfolio return prediction. Previous work has shown that portfolio optimization can be improved by using predicted stock earnings rather than historical earnings. We show that predicted portfolio returns can be improved by using ANFIS and taking as input a variety of technical and fundamental attributes about various indices of the stock market. To generate membership functions, we use a robust noise rejection-clustering algorithm. The neuro-fuzzy model is tested on portfolios constituted from the Tehran Stock Exchange. In our experiments, the proposed method performs better in predicting the portfolio return than the classical Markowitz portfolio optimization method, a multiple regression, a neural network, and the Sugeno–Yasukawa method. © 2010 Wiley Periodicals, Inc.