No abstract

This paper considers solving a biobjective urban transit routing problem with a genetic algorithm approach. The objectives are to minimize the passengers’ and operators’ costs where the quality of the route sets is evaluated by a set of parameters. The proposed algorithm employs an adding-node procedure which helps in converting an infeasible solution to a feasible solution. A simple yet effective route crossover operator is proposed by utilizing a set of feasibility criteria to reduce the possibility of producing an infeasible network. The computational results from Mandl’s benchmark problems are compared with other published results in the literature and the computational experiments show that the proposed algorithm performs better than the previous best published results in most cases.

This paper considers a new variant of the two-dimensional bin packing problem where each rectangle is assigned a due date and each bin has a fixed processing time. Hence the objective is not only to minimize the number of bins, but also to minimize the maximum lateness of the rectangles. This problem is motivated by the cutting of stock sheets and the potential increased efficiency that might be gained by drawing on a larger pool of demand pieces by mixing orders, while also aiming to ensure a certain level of customer service. We propose a genetic algorithm for searching the solution space, which uses a new placement heuristic for decoding the gene based on the best fit heuristic designed for the strip packing problems. The genetic algorithm employs an innovative crossover operator that considers several different children from each pair of parents. Further, the dual objective is optimized hierarchically with the primary objective periodically alternating between maximum lateness and number of bins. As a result, the approach produces several non-dominated solutions with different tradeoffs. Two further approaches are implemented. One is based on a previous Unified Tabu Search, suitably modified to tackle this revised problem. The other is randomized descent and serves as a benchmark for comparing the results. Comprehensive computational results are presented, which show that the Unified Tabu Search still works well in minimizing the bins, but the genetic algorithm performs slightly better. When also considering maximum lateness, the genetic algorithm is considerably better.

No abstract

Development of credit scoring models is important for financial institutions to identify defaulters and nondefaulters when making credit granting decisions. In recent years, artificial intelligence (AI) techniques have shown successful performance in credit scoring. Support Vector Machines and metaheuristic approaches have constantly received attention from researchers in establishing new credit models. In this paper, two AI techniques are reviewed with detailed discussions on credit scoring models built from both methods since 1997 to 2018. The main discussions are based on two main aspects which are model type with issues addressed and assessment procedures. Then, together with the compilation of past experiments results on common datasets, hybrid modelling is the state-of-the-art approach for both methods. Some possible research gaps for future research are identified.