Z.X. Guo

A multivariate intelligent decision-making model for retail sales forecasting

A sales forecasting problem in the retail industry is addressed based on early sales. An effective multivariate intelligent decision-making (MID) model is developed to provide effective forecasts for this problem by integrating a data preparation and preprocessing module, a harmony search-wrapper-based variable selection (HWVS) module and a multivariate intelligent forecaster (MIF) module. The HWVS module selects out the optimal input variable subset from given candidate inputs as the inputs of MIF. The MIF is established to model the relationship between the selected input variables and the sales volumes of retail products, and then utilized to forecast the sales volumes of retail products. Extensive experiments were conducted to validate the proposed MID model in terms of extensive typical sales datasets from real-world retail industry. Experimental results show that it is statistically significant that the proposed MID model can generate much better forecasts than extreme learning machine-based model and generalized linear model do.

A hybrid intelligent model for order allocation planning in make-to-order manufacturing

This paper investigated a multi-objective order allocation planning problem in make-to-order manufacturing with the consideration of various real-world production features. A novel hybrid intelligent optimization model, integrating a multi-objective memetic optimization (MOMO) process, a Monte Carlo simulation technique and a heuristic pruning technique, is developed to tackle this problem. The MOMO process, combining a NSGA-II optimization process with a tabu search, is proposed to provide Pareto optimal solutions. Extensive experiments based on industrial data are conducted to validate the proposed model. Results show that (1) the proposed model can effectively solve the investigated problem by providing effective production decision-making solutions; (2) the MOMO process has better capability of seeking global optimum than an NSGA-II-based optimization process and an industrial method.

A cloud-based intelligent decision-making system for order tracking and allocation in apparel manufacturing

This paper addressed the order tracking and allocation problem in an apparel manufacturing environment with multiple plants. A cloud-based intelligent decision-making system was developed to tackle this problem, which combined radio frequency identification and cloud computing technologies to capture real-time production records and make remote production order tracking, and employed computational intelligence techniques to generate effective order allocation solutions to appropriate plants. To evaluate the effectiveness of the proposed system, the system was implemented in an apparel manufacturing company with multiple plants, which reported distinct reductions in production costs and increases in production efficiency. This paper also investigated learning phenomenon in production and its effects on production efficiency and decision-making performance.

A bi-level evolutionary optimization approach for integrated production and transportation scheduling

The integrated scheduling problem is formulated as a bi-level mixed-integer nonlinear program.Consider unrelated parallel-machine environment and product batch-based delivery.An evolution-strategy-based bi-level evolutionary approach is developed.The proposed approach is superior to other 3 intelligent algorithms-based approaches. This paper investigates an integrated production and transportation scheduling (IPTS) problem which is formulated as a bi-level mixed integer nonlinear program. This problem considers distinct realistic features widely existing in make-to-order supply chains, namely unrelated parallel-machine production environment and product batch-based delivery. An evolution-strategy-based bi-level evolutionary optimization approach is developed to handle the IPTS problem by integrating a memetic algorithm and heuristic rules. The efficiency and effectiveness of the proposed approach is evaluated by numerical experiments based on industrial data and industrial-size problems. Experimental results demonstrate that the proposed approach can effectively solve the problem investigated.

The role of radio frequency identification (RFID) technologies in the textiles and fashion supply chain: an overview

Abstract: Barcode and radio frequency identification (RFID) technology have been widely applied in automatic identification and tracking throughout the textiles and fashion supply chain. This chapter will first compare the differences between these technologies and discuss how RFID technology can perform better than barcode technology in various aspects. The fundamentals of RFID technology, the architecture of an RFID system and an overview of the application of RFID technology in the textiles and fashion supply chain will be described.

The role of radio frequency identification (RFID) technologies in improving garment assembly line operations

Abstract: In this chapter, a production control problem on a flexible assembly line (FAL) with flexible operation assignment and variable operative efficiencies is described. A mathematical model of the production control problem is formulated by considering the time-constant learning curve to deal with the change of operative efficiency in real-life production. An intelligent production control decision support (PCDS) system is developed, composed of a radio frequency identification (RFID) technology-based data capture system and a PCDS model comprising a bi-level genetic optimization process, and a heuristic operation routing rule is developed. Experimental results demonstrated that the proposed PCDS system could implement effective production control decision-making.

Optimizing apparel production order planning scheduling using genetic algorithms

In this chapter the order scheduling problem at the factory level is investigated. Various uncertainties are considered and described as random variables. A mathematical model for this order scheduling problem is presented with the objectives of maximizing the total satisfaction level of all orders and minimizing their total throughput time. Uncertain completion time and beginning time of production process are derived from probability theory. A genetic algorithm is developed to seek after the optimal order scheduling solution. Experiments are conducted to validate the proposed algorithm by using real-world production data. The experimental results show the effectiveness of the proposed algorithm.

Intelligent apparel product cross-selling using radio frequency identification (RFID) technology for fashion retailing

Abstract: This chapter demonstrates how a combined use of radio frequency identification (RFID) technologies and the Intelligent Product Cross-selling System (IPCS) can improve cross- and up-selling in the retail industry. In this study, two systems have been developed, namely the Smart Dressing System (SDS) enabled by RFID technologies, and the IPCS. The SDS demonstrates a research endeavour in which, unlike the previous studies which focused on transactional data, customers’ in-store data can be collected using RFID-enabled SDS. This data can therefore be used for promoting or cross-selling new products to the customers more effectively and efficiently. The IPCS, integrating a rule-based expert system and a fuzzy screening technique, can handle the difficulties of processing linguistic and categorical information. This means fashion designers can recommend appropriate fashion product items for cross-selling with greater ease. The proposed systems’ ability to improve selling strategies for the fashion retail industry will in turn help to increase their sales performance.

Fundamentals of artificial intelligence techniques for apparel management applications

The fundamentals of artificial intelligence (AI) techniques are introduced briefly in this chapter. The definition, significance and classification of AI techniques are presented first. Some representative AI techniques, especially those which have been used in solving decision-making problems in the apparel supply chain operations, are then introduced to help readers understand AI techniques used in subsequent chapters. These techniques include rule-based expert systems, evolutionary optimization techniques, feedforward neural networks and fuzzy logic. Their relevant fundamentals are introduced, including their origins, fundamental characteristics, possible applications and the procedures of implementation.