Tsan-Ming Choi

Sales forecasting using extreme learning machine with applications in fashion retailing

Sales forecasting is a challenging problem owing to the volatility of demand which depends on many factors. This is especially prominent in fashion retailing where a versatile sales forecasting system is crucial. This study applies a novel neural network technique called extreme learning machine (ELM) to investigate the relationship between sales amount and some significant factors which affect demand (such as design factors). Performances of our models are evaluated by using real data from a fashion retailer in Hong Kong. The experimental results demonstrate that our proposed methods outperform several sales forecasting methods which are based on backpropagation neural networks.

Mean-variance analysis of a single supplier and retailer supply chain under a returns policy

Abstract In the literature, most of the supply chain coordinating policies target at improving the supply chain’s efficiency in terms of expected cost reduction or expected profit improvement. However, optimizing the expected performance alone cannot guarantee that the realized performance measure will fall within a small neighborhood of its expected value when the corresponding variance is high. Moreover, it ignores the risk aversion of supply chain members which may affect the achievability of channel coordination. As a result, we carry out in this paper a mean–variance (MV) analysis of supply chains under a returns policy. We first propose an MV formulation for a single supplier single retailer supply chain with a newsvendor type of product. The objective of each supply chain decision maker is to maximize the expected profit such that the standard deviation of profit is under the decision maker’s control. We study both the cases with centralized and decentralized supply chains. We illustrate how a returns policy can be applied for managing the supply chains to address the issues such as channel coordination and risk control. Extensive numerical studies are conducted and managerial findings are proposed.

A Neuro-Fuzzy Inference System Through Integration of Fuzzy Logic and Extreme Learning Machines

This paper investigates the feasibility of applying a relatively novel neural network technique, i.e., extreme learning machine (ELM), to realize a neuro-fuzzy Takagi-Sugeno-Kang (TSK) fuzzy inference system. The proposed method is an improved version of the regular neuro-fuzzy TSK fuzzy inference system. For the proposed method, first, the data that are processed are grouped by the k-means clustering method. The membership of arbitrary input for each fuzzy rule is then derived through an ELM, followed by a normalization method. At the same time, the consequent part of the fuzzy rules is obtained by multiple ELMs. At last, the approximate prediction value is determined by a weight computation scheme. For the ELM-based TSK fuzzy inference system, two extensions are also proposed to improve its accuracy. The proposed methods can avoid the curse of dimensionality that is encountered in backpropagation and hybrid adaptive neuro-fuzzy inference system (ANFIS) methods. Moreover, the proposed methods have a competitive performance in training time and accuracy compared to three ANFIS methods.

Mean-variance analysis of supply chains under wholesale pricing and profit sharing schemes

In this paper, we explore the use of a wholesale pricing and profit sharing scheme (WPPS) for coordinating supply chains under the mean-variance (MV) decision framework. We first analytically establish the necessary and sufficient conditions for coordinating the centralized supply chain by WPPS. We then show that there exists a unique equilibrium of the Stackelberg game with WPPS in the decentralized case. After that, we discuss the information asymmetric case in which the retailer can be benefited by pretending to be more risk averse. Finally, we propose a new measure for the manufacturer to prevent this cheating from happening. Insights are generated.

Optimal returns policy for supply chain with e-marketplace

Abstract We study in this paper a supply chain which is integrated by a returns policy. In the past, owing to a lack of sales channels, the returned products would worth very little. Now, with the advance of the e-commerce, the returned products can be sold with a higher price on the e-marketplace. In light of this, we first investigate the optimal returns policy under the existence of the e-marketplace. Through a mean–variance analysis, we further study the risk issue associated with the optimal policy. Extensive simulations are then carried out and the managerial insights are discussed.

Optimal two-stage ordering policy with Bayesian information updating

We investigate in this paper an optimal two-stage ordering policy for seasonal products. Before the selling season, a retailer can place orders for a seasonal product from her supplier at two distinct stages satisfying the lead-time requirement. Market information is collected at the first stage and is used to update the demand forecast at the second stage by using Bayesian approach. The ordering cost at the first stage is known but the ordering cost at the second stage is uncertain. A two-stage dynamic optimization problem is formulated and an optimal policy is derived using dynamic programming. The optimal ordering policy exhibits nice structural properties and can easily be implemented by a computer program. The detailed implementation scheme is proposed. The service level and profit uncertainty level under the optimal policy are discussed. Extensive numerical analyses are carried out to study the performance of the optimal policy.

Price, Rebate, and Returns Supply Contracts for Coordinating Supply Chains with Price Dependent Demand

Channel rebates and returns policies are common mechanisms for manufacturers to entice retailers to increase their order quantities and sales ultimately. However, when the underlying demand depends on the retail price, it has been known that channel coordination cannot be achieved if only one of these mechanisms is deployed. In this paper, we show that a policy that combines the use of wholesale price, channel rebate, and returns can coordinate a channel with both additive and multiplicative price-dependent demands. In addition to determining the sufficient conditions for the contract parameters associated with the equilibrium policy, we show that multiple equilibrium policies for channel coordination exist. We further explore how the equilibrium policy can be adjusted to achieve Pareto improvement. Other issues such as the maximum amount of expected profit that the manufacturer can share under the coordinated channel, the structural properties of the contracts under both the additive and multiplicative price-dependent demand functions are also discussed.

Mean–Variance Analysis for the Newsvendor Problem

The newsvendor problem is a fundamental building block for inventory management with a stochastic demand. The classical newsvendor problem focuses on a sole objective of either minimizing the expected cost or maximizing the expected profit. However, the performance measure with expected value alone is insufficient, and it ignores the risk preferences of the decision makers. As a result, we carry out a mean-variance analysis of the newsvendor problem. We construct analytical models and reveal the problems structural properties. We propose the solution schemes which help to identify the optimal solutions. Interesting findings regarding the efficient frontier, the case with a stockout penalty cost, and the safety-first objective are discussed.

Supply chain risk analysis with mean-variance models: a technical review

Pioneered by Nobel laureate Harry Markowitz in the 1950s, the mean-variance (MV) formulation is a fundamental theory for risk management in finance. Over the past decades, there is a growing popularity of applying this ground breaking theory in analyzing stochastic supply chain management problems. Nowadays, there is no doubt that the mean-variance (MV) theory is a well-proven approach for conducting risk analysis in stochastic supply chain operational models. In view of the growing importance of MV approach in supply chain management, we review a selection of related papers in the literature that focus on MV analytical models. By classifying the literature into three major areas, namely, single-echelon problems, multi-echelon supply chain problems, and supply chain problems with information updating, we derive insights into the current state of knowledge in each area and identify some associated challenges with a discussion of some specific models. We also suggest future research directions on topics such as information asymmetry, supply networks, and boundedly rational agents, etc. In conclusion, this paper provides up-to-date information which helps both academicians and practitioners to better understand the development of MV models for supply chain risk analysis.

Coordination Mechanism for the Supply Chain with Leadtime Consideration and Price-Dependent Demand

We study a coordination contract for a supplier-retailer channel producing and selling a fashionable product exhibiting a stochastic price-dependent demand. The products selling season is short, and the supply chain faces great demand uncertainty. We consider a scenario where the supplier reserves production capacity for the retailer in advance, and permits the retailer to place an order not exceeding the reserved capacity after a demand information update during a leadtime. We formulate a two-stage optimization problem in which the supplier decides the amount of capacity reservation in the first stage, and the retailer determines the order quantity and the retail price after observing the demand information in the second stage. We propose a three-parameter risk and profit sharing contract that coordinates the supply chain. The proposed contract permits any agreed-upon division of the supply-chain profit between the channel members.