應用離散型粒子群演算法於網路商店商品圖片配置及庫存管理之研究

Discrete Particle Swarm Optimization for Online Store Product Placement and Inventory Management

施貫中(Kuan-Chung Shih)

指導教授 ： 陳彥匡

國立臺中科技大學/資訊與流通學院/流通管理系碩士班/碩士(2018年)

摘要

網路的普及化驅使電子商務快速發展，促使許多傳統零售商店轉變型態朝向網路開設商店，在網路商店上該如何吸引消費者的目光，讓更多消費者進而消費，成為企業重要的獲利關鍵之一，故若能將網路商店的商品圖片配置與庫存管理得當，可以有效增加網路商店業者的獲利。
本研究主要是解決網路商店商品圖片配置及庫存管理問題，並應用學者提出的VADD模型與離散型粒子群演算法進行求解，再將求解結果與離散型基因演算法進行求解結果之比較分析，據此提出本研究之結論與建議。
由研究結果可得知，在本研究所進行的六個品項、十個品項、十八個品項的實驗求解結果，發現離散型粒子群演算法求解效率皆優於離散型基因演算法，進一步再以多組VADD模型參數進行敏感度分析，經分析發現離散型粒子群演算法相對於離散型基因演算法的執行時間改善率達50%以上，且其各個因子皆無顯著差異，表示離散型粒子群演算法執行時間極具穩定性，不會因為模型參數變動而影響求解效率。
綜上，本研究在學術的貢獻為將傳統的粒子群演算法及基因演算法轉換成適用於離散型變數的演算法，以適用在離散型決策變數的最佳化模型求解；在實務的貢獻則是透過本研究所提出的離散型粒子群演算法可輔助網路商店業者在短時間內動態調整商品圖片配置及庫存，藉此提升網路商店的銷售業績。

關鍵字

網路商店 ； 商品圖片配置 ； 庫存管理 ； 離散型粒子群演算法

並列摘要

The popularization of the Internet has driven the rapid development of e-commerce, prompting many traditional retail shops to change their business models towards the Internet. Therefore, how to attract consumers' attention in online stores and allow more consumers to consume are becoming one of the important profit resources. Moreover, if the online store’s product placement and inventory management can be properly managed, it can effectively increase the profit of online store operators.
This research aims to propose a discrete particle swarm optimization (DPSO) method to solve the visual-attention-dependent demand (VADD) model for the product placement and inventory management problem with online store. In order to conform the VADD model, this research converts the traditional PSO into a method suitable for discrete variables. Then through the experimental analysis to compare the results of the solution method.
This research result shows that the efficiency of the proposed method is better than the DGA method in terms of their average execution time. In a sensitivity analysis shows that the execution time improvement rate of the DPSO relative to the DGA was more than 50%. Also, there was no significant difference among its various factors and the execution time of the DPSO was extremely stable and solution efficiency isn't affected by changes in model parameters.
Therefore, in academic contributions, this research presents a DPSO method to solve the VADD model. In practical contributions, this method can help online store operators rapidly and dynamically make decisions on product placement and inventory management to increase the sales of goods and profits of online store.

並列關鍵字

Online Store ； Product Placement ； Inventory Management ； Discrete Particle Swarm Optimization (DPSO)

參考文獻

Angehrn, A. (1997). Designing mature internet business strategies: the ICDT model. European Management Journal, 15(4), 361-369.

APICS (2007). APICS Operations Management Body of Knowledge Framework, Retrieved from http://www.apics.org/

Bagheri, A., Zandieh, M., Mahdavi, I., & Yazdani, M. (2010). An artificial immune algorithm for the flexible job-shop scheduling problem. Future Generation Computer Systems, 26(4), 533-541.

Bai, X., Yan, W., Ge, S. S., & Cao, M. (2018). An integrated multi-population genetic algorithm for multi-vehicle task assignment in a drift field. Information Sciences, 453, 227-238.

Baykasoğlu, A., Hamzadayi, A., & Köse, S. Y. (2014). Testing the performance of teaching–learning based optimization (TLBO) algorithm on combinatorial problems: Flow shop and job shop scheduling cases. Information Sciences, 276, 204-218.