Mu- Chen

Credit scoring and rejected instances reassigning through evolutionary computation techniques

Abstract The credit industry is concerned with many problems of interest to the computation community. This study presents a work involving two interesting credit analysis problems and resolves them by applying two techniques, neural networks (NNs) and genetic algorithms (GAs), within the field of evolutionary computation. The first problem is constructing NN-based credit scoring model, which classifies applicants as accepted (good) or rejected (bad) credits. The second one is better understanding the rejected credits, and trying to reassign them to the preferable accepted class by using the GA-based inverse classification technique. Each of these problems influences on the decisions relating to the credit admission evaluation, which significantly affects risk and profitability of creditors. From the computational results, NNs have emerged as a computational tool that is well-matched to the problem of credit classification. Using the GA-based inverse classification, creditors can suggest the conditional acceptance, and further explain the conditions to rejected applicants. In addition, applicants can evaluate the option of minimum modifications to their attributes.

Mining changes in customer behavior in retail marketing

During the past decade, there have been a variety of significant developments in data mining techniques. Some of these developments are implemented in customized service to develop customer relationship. Customized service is actually crucial in retail markets. Marketing managers can develop long-term and pleasant relationships with customers if they can detect and predict changes in customer behavior. In the dynamic retail market, understanding changes in customer behavior can help managers to establish effective promotion campaigns. This study integrates customer behavioral variables, demographic variables, and transaction database to establish a method of mining changes in customer behavior. For mining change patterns, two extended measures of similarity and unexpectedness are designed to analyze the degree of resemblance between patterns at different time periods. The proposed approach for mining changes in customer behavior can assist managers in developing better marketing strategies.

Evaluating the cross-efficiency of information sharing in supply chains

Supply chain management integrates the intra- and inter-corporate processes as a whole system. Through information technology, companies can efficiently manage the product flow and information related to the issues such as production capacity, customer demand and inventory at lower costs. Information sharing can significantly improve the performance of the supply chain, how the different combination of information sharing affects the performance is not yet understood. This study designs different information-sharing scenarios to analyze the supply chain performance through a simulation model. Since there are not only desirable measures but also undesirable measures in supply chains, the usual data envelopment analysis (DEA) model allows measuring performance for complete weight flexibility. In this paper, a cross-efficiency DEA approach is applied to solve this problem. We identify the most efficient scenario and estimate the each efficiency of information-sharing scenarios. Contrary to the previous findings in the literature suggesting sharing as much as information possible to increase benefits, the results of this study show that the scenario of demand information sharing is the most efficient one. In addition, sharing information on capacity and demand, and full information sharing in general are good practices. Sharing only information on capacity and/or inventory information, without sharing information on demand, interferes with production at manufacturers, and causes misunderstandings, which can magnify the bullwhip effect.

Batching orders in warehouses by minimizing travel distance with genetic algorithms

The power of warehousing system to rapidly respond to customer demands participates an important function in the success of supply chain. Before picking the customer orders, effectively consolidating orders into batches can significantly speed the product movement within a warehouse. There is considerable product movement within a warehouse; the warehousing costs can be reduced by even a small percentage of reduction in the picking distance. The order batching problem is recognized to be NP-hard, and it is extremely difficult to obtain optimal solutions for large-scale problems within a tolerable computation time. Previous studies have mainly focused on the order batching problems in warehouses with a single-aisle and two-dimension layout. This study develops an order batching approach based on genetic algorithms (GAs) to deal with order batching problems with any kind of batch structure and any kind of warehouse layout. Unlike to previous batching methods, the proposed approach, additionally, does not require the computation of order/batch proximity and the estimation of travel distance. The proposed GA-based order batching method, namely GABM, directly minimizes the total travel distance. The potential of applying GABM for solving medium- and large-scale order batching problems is also investigated by using several examples. From the batching results, the proposed GABM approach appears to obtain quality solutions in terms of travel distance and facility utilization.

The adaptive approach for storage assignment by mining data of warehouse management system for distribution centres

Among distribution centre operations, order picking has been reported to be the most labour-intensive activity. Sophisticated storage assignment policies adopted to reduce the travel distance of order picking have been explored in the literature. Unfortunately, previous research has been devoted to locating entire products from scratch. Instead, this study intends to propose an adaptive approach, a Data Mining-based Storage Assignment approach (DMSA), to find the optimal storage assignment for newly delivered products that need to be put away when there is vacant shelf space in a distribution centre. In the DMSA, a new association index (AIX) is developed to evaluate the fitness between the put away products and the unassigned storage locations by applying association rule mining. With AIX, the storage location assignment problem (SLAP) can be formulated and solved as a binary integer programming. To evaluate the performance of DMSA, a real-world order database of a distribution centre is obtained and used to compare the results from DMSA with a random assignment approach. It turns out that DMSA outperforms random assignment as the number of put away products and the proportion of put away products with high turnover rates increase.

Prediction model building and feature selection with support vector machines in breast cancer diagnosis

Breast cancer is a serious problem for the young women of Taiwan. Some medical researches have proved that DNA viruses are one of the high-risk factors closely related to human cancers. Five DNA viruses are studied in this research: specific types of HSV-1 (herpes simplex virus type 1), EBV (Epstein-Barr virus), CMV (cytomegalovirus), HPV (human papillomavirus), and HHV-8 (human herpesvirus-8). The purposes of this study are to obtain the bioinformatics about breast tumor and DNA viruses, and to build an accurate diagnosis model about breast cancer and fibroadenoma. Research efforts have reported with increasing confirmation that the support vector machine (SVM) has a greater accurate diagnosis ability. Therefore, this study constructs a hybrid SVM-based strategy with feature selection to render a diagnosis between the breast cancer and fibroadenoma and to find the important risk factor for breast cancer. The results show that {HSV-1, HHV-8} or {HSV-1, HHV-8, CMV} are the most important features and that the diagnosis model achieved high classification accuracy, at 86% of average overall hit rate. A Linear discriminate analysis (LDA) diagnosis model is also constructed in this study. The LDA model shows that {HSV-1, HHV-8, EBV} or {HSV-1, HHV-8} are significant factors which are similar to that of the SVM-based classifier. However, the classificatory accuracy of the SVM-based classifier is slightly better than that of LDA in the negative hit ratio, positive hit ratio, and overall hit ratio.

The impact of website quality on customer satisfaction and purchase intention: perceived playfulness and perceived flow as mediators

The purposes of this study are to examine whether perceived playfulness and perceived flow would mediate the relationships among website quality, customer satisfaction, and purchase intention, as well as to assess the degree of reciprocity between perceived playfulness and perceived flow in an online travel agency context. This study suggested a research framework for testing the relationships among the constructs based on the stimulus-organism-response framework. In addition, this study developed a non-recursive model. After validating the measurement scales, empirical analyses were conducted using structural equation modelling. The findings confirm that website quality affects customers’ perceived playfulness and perceived flow, and in turn, would influence their satisfaction and purchase intention. Notably, this study finds that the service quality is more important than information and system quality in influencing customer satisfaction and purchase intention. Furthermore, the study reveals that the relationship between perceived playfulness and perceived flow is reciprocal. Based on the findings, the implications are discussed in the paper and directions for future research are also highlighted.

Evaluating the supply chain performance of IT-based inter-enterprise collaboration

With the use of IT, the nature of business processes has changed from intra- to cross-enterprise. This has significantly altered enterprise interactions with suppliers and customers. Collaboration is essential for successful supply chain performance. In recent years a variety of initiatives have been adopted by industries. These attempted to create efficiency and effectiveness through integration of the activities and processes. However, enterprises can only gain significant benefits by mass collaboration. Collaborative Planning, Forecasting and Replenishment (CPFR), which result in deeper partnerships, have become an important factor in supply chains. We investigated the performance of CPFR; it possesses formalized guidelines and is a relatively new initiative. By using simulation, we investigated four CPFR alternatives that are used in the adoption of collaboration strategies in industries. Retailers have traditionally played the hub role in supply chains in order to reduce the bullwhip effect, but our simulation confirmed that shifting the retailer (buyer-driven) collaboration to a manufacturer (supplier-driven) approach was a more viable option.

Aggregation of orders in distribution centers using data mining

This paper considers the problem of constructing order batches for distribution centers using a data mining technique. With the advent of supply chain management, distribution centers fulfill a strategic role of achieving the logistics objectives of shorter cycle times, lower inventories, lower costs and better customer service. Many companies consider both their cost effectiveness and market proficiency to depend primarily on efficient logistics management. Warehouse management system (WMS) presently is considered a key to strengthening company logistics. Order picking is routine in distribution centers. Before picking a large set of orders, effectively grouping orders into batches can accelerate product movement within the storage zone. The order batching procedure has to be implemented in WMS and may be run online many times daily. The literature has proposed numerous batching heuristics for minimizing travel distance or travel time. This paper presents a clustering procedure for an order batching problem in a distribution center with a parallel-aisle layout. A data mining technique of association rule mining is adopted to develop the order clustering approach. Performance comparisons between the developed approach and existing heuristics are given for various problems.

Ranking discovered rules from data mining with multiple criteria by data envelopment analysis

In data mining applications, it is important to develop evaluation methods for selecting quality and profitable rules. This paper utilizes a non-parametric approach, Data Envelopment Analysis (DEA), to estimate and rank the efficiency of association rules with multiple criteria. The interestingness of association rules is conventionally measured based on support and confidence. For specific applications, domain knowledge can be further designed as measures to evaluate the discovered rules. For example, in market basket analysis, the product value and cross-selling profit associated with the association rule can serve as essential measures to rule interestingness. In this paper, these domain measures are also included in the rule ranking procedure for selecting valuable rules for implementation. An example of market basket analysis is applied to illustrate the DEA based methodology for measuring the efficiency of association rules with multiple criteria.