以產品銷售數據分析優化倉儲管理系統｜國立清華大學博碩士論文庫

簡易檢索 / 詳目顯示

回結果列表

研究生：	翁芸琇 Ang, Abigail Joyce
論文名稱：	以產品銷售數據分析優化倉儲管理系統 Optimization of Inventory Control and Management System using Product Data
指導教授：	祁玉蘭 Chyi, Yih-Luan
口試委員:	周瑞賢 Chou, Jui-Hsien 許鈺珮 Hsu, Yu-Pei
學位類別：	碩士 Master
系所名稱：	科技管理學院 - 國際專業管理碩士班 International Master of Business Administration(IMBA)
論文出版年：	2021
畢業學年度：	109
語文別：	英文
論文頁數：	53
中文關鍵詞：	庫存、庫存管理、庫存優化、預測、人工神經網絡、循環神經網絡 (RNN) 、差分整合移動平均自迴歸模型 (ARIMA)
外文關鍵詞：	Inventory, Inventory Control and Management System, Inventory Optimization, Recurrent Neural Network (RNN), Auto-Regressive Integrated Moving Average (ARIMA)
相關次數：	點閱：3 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

庫存控制系統正越來越廣泛地實施，因為其提供複雜的庫存管理解決方案。然而庫存控制系統需要有效且高效的分析程序、優化系統和預測方法。庫存控制管理系統旨在找出補貨的最佳數量，以避免過多的存貨和相關成本。本論文旨在設計出優化選擇的庫存補貨策略，來確定每張訂單週期的最低補貨價格和數量，以增強小型企業的庫存控制和管理。總體而言，兩種預測分析方法，長短期記憶模型和差分整合移動平均自迴歸模型，被應用於評估庫存控制系統的性能指標。藉由計算並比較兩個模型的殘差平方和 (RSS) ，預測精度度量如平均絕對偏差 (MAD)、均方誤差 (MSE) 和均方根誤差 (RMSE)。我們選擇長短期記憶模型為較佳的模型，因為模擬結果顯示了最低的成本和相對應的庫存數量，並且長短期記憶模型是所有方法中能夠實現方案目標函數的最理想選擇。最後此建議的庫存控制管理系統將能降低計算能力並維持最適合所選商品的庫存策略。

An inventory control and management system is becoming more extensively implemented as it provides complicated inventory management solutions. However, efficient and effective analytical procedures, optimization systems, and forecasting methods are required. The inventory control and management system aims to guide the optimal quantities for stock replenishment to avoid maintaining excessive inventory and its associated cost. This thesis designs the optimization of a chosen inventory replenishment strategy wherein the minimum price and quantities of replenishment per order cycle are determined to enhance the inventory control and management of a small business. Overall, two predictive analytical methods, namely the Recurrent Neural Network (RNN) using the Long-Short Term Memory (LSTM) model and the Auto-Regressive Integrated Moving Average (ARIMA) model, have been applied to evaluate the performance measure for the proposed scheme. The Residual Sum of Square (RSS) values and forecast accuracy measures such as the Mean Absolute Deviation (MAD), Mean Square Error (MSE), and Root Mean Square Error (RMSE) of the two models were calculated and compared. The better model, namely the RNN using the Long-Short term memory model, was chosen. The simulation results reveal the lowest costs and corresponding quantities associated with the selected model. Moreover, it is the most ideal among all the methods that can fulfill the objective function of this proposed scheme. In addition, the proposed inventory control management system will reduce computation power and sustain the inventory strategy that is the most suitable to the chosen commodity.

ABSTRACT                                                   ii
I. INTRODUCTION                                            1
II. LITERATURE REVIEW                                      4
2.1 Artificial Neural Networks                             7
2.2 Auto-Regressive Integrated Moving Average              9
III. RESEARCH METHODOLOGY                                  10
3.1 Problem Statement                                      10
3.2 Inventory Strategies                                   11
3.3 Methodology                                            15
IV. RESULTS & DISCUSSION                                   27
4.1 The Data                                               27
4.2 Results                                                28
4.3 Research Limitations                                   33
4.4 Alternatives and Recommendations for Future Research   35
V. CONCLUSION                                              40
REFERENCES                                                 42
APPENDIX                                                   47

Table of figures
Fig.1. Supply chain of the ABC company                     2
Fig.2. Structure of an Artificial Neural Network           7
Fig.3. Single Layer Feedforward Network                    8
Fig.4. Multilayer Feedforward Network                      8
Fig.5. Recurrent Neural Network                            8
Fig.6. Fixed-point Order Policy                            12
Fig.7. (s, S) order Policy                                 13
Fig.8. Structure of Proposed Method                        16
Fig.9. Training error                                      21

Table
Table 1: Parameters of an Auto-Regressive Integrated Moving Average Model                                                      9
Table 2: Summary of Sequential Keras Model                 20
Table 3: ADF test results                                  22
Table 4: KPSS test results                                 22
Table 5: ARIMA model results                               23
Table 6: Residual Sum of Square Comparison                 24
Table 7: Meaures of forecast accuracy for the RNN-based LSTM model
25
Table 8: Measure of forecast accuracy for the ARIMA-based time series forecasting                                                25
Table 9: Optimization Parameters                           26
Table 10: Costs and Prices associated with Chocolate Chips 27
Table 11: Summary Statistics of the Dataset                28
Table 12: Forecasted sales values of the commodity chocolate chips [RNN-based LSTM] (April 2021- July 2021)                        29
Table 13: Forecasted sales values of the commodity chocolate chips [ARIMA] (April 2021- July 2021)                            29
Table 14: Minimum replenishment costs for each low-level inventory s
30
Table 15: Parameters & Optimized Results (April 2021- July 2021)
30

                                

[1] Abbasimehr, H., & Shabani, M. (2020). “Forecasting of customer behavior using time series
analysis”. Data Science: From Research to Application, 188-201.
https://doi.org/10.1007/978-3-030-37309-2_15

[2] Abdelmaguid, F., & Dessouky, M. (2007). “A genetic algorithm approach to the integrated inventory-distribution problem”. International Journal of Production Research, 44(21), 4445- 4464. https://doi.org/10.1080/00207540600597138

[3] Al-Hoqani, W. M. (2017). “Recommendation of new semi-automated approach of decision tree diagram”. 2017 Computing Conference. https://doi.org/10.1109/sai.2017.8252231

[4] Baker, R. C., & Urban, T. L. (1988). “A deterministic inventory system with an inventory-level-Dependent demand rate”. Journal of the Operational Research Society, 39(9), 823-831. https://doi.org/10.1057/jors.1988.142

[5] Beamon, B. M. (1998). “Supply chain design and analysis: Models and methods”. International Journal of Production Economics, 55(3), 281-294.
https://doi.org/10.1016/s0925-5273(98)00079-6

[6] Bishop, T. (2017). “The cost of convenience: Amazon’s shipping losses top $7B for first time. GeekWire”. 19(2). https://www.geekwire.com/2017/true-cost-convenience-amazons-annual-shipping-losses-top-7b-first-time/

[7] Biswas, S., & Sinha, M. (2021). “Performances of deep learning models for Indian Ocean wind speed prediction”. Modeling Earth Systems and Environment, 7(2), 809-831.
https://doi.org/10.1007/s40808-020-00974-9

[8] Brownlee, J. (2017). “Time series forecasting with the long short-term memory network in Python”. Machine Learning Mastery, xi-xiv.
https://doi.org/10.1017/cbo9781139198721.001

[9] Chang, C., Goyal, S. K., & Teng, J. (2006). On “An EOQ model for perishable items under stock-dependent selling rate and time-dependent partial backlogging by Dye and Ouyang”. European Journal of Operational Research, 174(2), 923-929.
https://doi.org/10.1016/j.ejor.2005.04.024

[10] Chang, C., Teng, J., & Chern, M. (2010). “Optimal manufacturer’s replenishment policies for deteriorating items in a supply chain with up-stream and down-stream trade credits”. International Journal of Production Economics, 127(1), 197-202.
https://doi.org/10.1016/j.ijpe.2010.05.014

[11] Cheng, W., & Hüllermeier, E. (2009). “Combining instance-based learning and logistic regression for multilabel classification”. Machine Learning, 76(2-3), 211-225.
https://doi.org/10.1007/s10994-009-5127-5

[12] Chmielewski, S., Samulowska, M., Lupa, M., Lee, D., & Zagajewski, B. (2018). “Citizen science and WebGIS for outdoor advertisement visual pollution assessment”. Computers, Environment and Urban Systems, 67, 97-109.
https://doi.org/10.1016/j.compenvurbsys.2017.09.001

[13] Chopra. (2015). “Linear shipping connectivity index versus trade costs”.
https://doi.org/10.1787/aid_glance-2015-graph28-en

[14] Cárdenas-Barrón, L. E., Treviño-Garza, G., & Wee, H. M. (2012). “A simple and better algorithm to solve the Vendor Managed Inventory control system of multi-product multi-constraint economic order quantity model”. Expert Systems with Applications, 39(3), 3888-3895. https://doi.org/10.1016/j.eswa.2011.09.057

[15] Drechsel, M. (2017). Commodity booms and busts in emerging Audi VR economies. https://doi.org/10.3386/w23716

[16] Fattah, J., Ezzine, L., Aman, Z., El Moussami, H., & Lachhab, A. (2018). “Forecasting of demand using ARIMA model”. International Journal of Engineering Business Management, 10, 184797901880867. https://doi.org/10.1177/1847979018808673

[17] Guo, X., Liu, C., Xu, W., Yuan, H., & Wang, M. (2014). “A prediction-based inventory optimization using data mining models”. 2014 Seventh International Joint Conference on Computational Sciences and Optimization. https://doi.org/10.1109/cso.2014.118

[18] Hillier, F., & Lieberman, G. (2021). Chapter 18: Inventory Theory. Introduction to Operations Research, McGraw-Hill Education, (11), 935-987.
https://doi.org/10.2307/2287800

[19] Hochreiter, S., & Schmidhuber, J. (1997). “Long short-term memory”. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735

[20] Jiang, Q., & Xing, W. (2015). “An optimization model for inventory system based on supply-demand balance”. Proceedings of the 2015 International Conference on Modeling, Simulation and Applied Mathematics. https://doi.org/10.2991/msam-15.2015.37

[21] Lazzeri, F. (2020). “Chapter 6: Model Deployment for Time Series Forecasting”. “ARIMA Model–Complete Guide to Time Series Forecasting in Python”. Machine Learning for Time Series Forecasting with Python®, 167-196.
https://doi.org/10.1002/9781119682394.ch6

[22] Malik, M. (2020). “Chapter 3: Neural Networks from Scratch in Python”. Essay. In Deep Learning Crash Course for Beginners with Python, AI Publishing, 79-96.
https://doi.org/10.1007/978-1-4842-2766-4_6

[23] Mandal, B. N., & Phaujdar, S. (1989). “An inventory model for deteriorating items and stock-dependent consumption rate”. Journal of the Operational Research Society, 40(5), 483-488. https://doi.org/10.1057/jors.1989.75

[24] Mbah, T. J., Ye, H., Zhang, J., & Long, M. (2021). “Using LSTM and ARIMA to Simulate and Predict Limestone Price Variations”. Mining, Metallurgy & Exploration. https://doi.org/10.4236/ojg.2020.1012063

[25] Mwambe, O., Tan, P., Kamioka., E. (2020). “Comparative analysis of local and international credit rating assessments of Tanzanian commercial banks”. Diss. The University of Dodoma, 10(2), 42. https://doi.org/10.3390/educsci10020042

[26] Packowski, J. (2013). “Chapter: Tactical LEAN Supply Chain Planning Parameterization”. LEAN Supply Chain Planning, 237-306.
https://doi.org/10.1201/b16084-14

[27] Pasandideh, S. H., Niaki, S. T., & Nia, A. R. (2011). “A genetic algorithm for Vendor Managed Inventory control system of multi-product multi-constraint economic order quantity model”. Expert Systems with Applications, 38(3), 2708-2716.
https://doi.org/10.1016/j.eswa.2010.08.060

[28] Patel, H. H., & Prajapati, P. (2018). “Study and analysis of decision tree based classification algorithms”. International Journal of Computer Sciences and Engineering, 6(10), 74-78. https://doi.org/10.26438/ijcse/v6i10.7478

[29] Radhakrishnan, P., Prasad, V., & Gopalan, M. (2009). “Optimizing inventory using genetic algorithm for efficient supply chain management”. Journal of Computer Science, 5(3), 233-241. https://doi.org/10.3844/jcs.2009.233.241

[30] Roy, T., & Chaudhuri, K. (2011). “A finite time horizon EOQ model with ramp-type demand rate under inflation and time-discounting”. International Journal of Operational Research, 11(1), 100. https://doi.org/10.1504/ijor.2011.040330

[31] Spanke, M. (2020). “Chapter: Pickup and Returns”. In: “Retail Isn't Dead”.
Palgrave Macmillan, Cham, 95-100. https://doi.org/10.1007/978-3-030-36650-6_12

[32] Terblanche, N. S., & Boshoff, C. (2004). “The in-store shopping experience: A comparative study of supermarket and clothing store customers”. South African Journal of Business Management, 35(4), 1-10. https://doi.org/10.4102/sajbm.v35i4.663

簡易檢索 / 詳目顯示

相關論文