應用機器學習回歸模型於成衣製造業銷售預測-以T公司為例

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：53

、訪客IP：3.145.152.49

姓名

王禎祥(Jason Wang) 查詢紙本館藏

畢業系所

資訊管理學系在職專班

論文名稱

應用機器學習回歸模型於成衣製造業銷售預測-以T公司為例
(Applying machine learning regression models for sales forecasting of the garment manufacturing industry-An empirical study on T manufacturing company)

相關論文

★ 利用資料探勘技術建立商用複合機銷售預測模型	★ 應用資料探勘技術於資源配置預測之研究-以某電腦代工支援單位為例
★ 資料探勘技術應用於航空業航班延誤分析-以C公司為例	★ 全球供應鏈下新產品的安全控管-以C公司為例
★ 資料探勘應用於半導體雷射產業-以A公司為例	★ 應用資料探勘技術於空運出口貨物存倉時間預測-以A公司為例
★ 使用資料探勘分類技術優化YouBike運補作業	★ 特徵屬性篩選對於不同資料類型之影響
★ 資料探勘應用於B2B網路型態之企業官網研究-以T公司為例	★ 衍生性金融商品之客戶投資分析與建議-整合分群與關聯法則技術
★ 應用卷積式神經網路建立肝臟超音波影像輔助判別模型	★ 基於卷積神經網路之身分識別系統
★ 能源管理系統電能補值方法誤差率比較分析	★ 企業員工情感分析與管理系統之研發
★ 資料淨化於類別不平衡問題: 機器學習觀點	★ 資料探勘技術應用於旅客自助報到之分析—以C航空公司為例

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

在服飾產業的快時尚潮流下，終端客戶的需求具有相當大的不確定性，而紡織產業鏈屬中下游的成衣製造業之商業模式大都為B2B，客戶通常是國際時尚品牌零售商如GAP、H&M、ZARA等，零售商為了降低成本與風險，訂單大都是以少量多樣交期短的型式，成衣製造業需配合客戶進行快速回應的協同管理來因應，然而在供應鏈的長鞭效應下，庫存成本的高低是直接影響利潤高低的關鍵因素之一，因此需要對市場需求更加敏銳，銷售預測的準確與否將是改善獲利及快速回應的關鍵，其並可優化生產和需求計劃，使得供應鏈的運作更有效率及快速，並減少浪費與節省成本。
本研究以國內上市的成衣製造的供應商為例，其銷售預測是仰賴業務人員以主觀經驗、過往客戶銷售相關數據與訂單透明度等資訊，整合進行人工的銷售預測，然而對銷售歷史大數據資料並無良好的大數據分析工具來協助銷售預測。研究證實使用適量的銷售歷史資料應用於機學習回歸模型確實能改善銷售預測的錯誤率。本研究進行初步的機器模型預測績效比較，實驗結果顯示，本研究個案的各資料集的預測績效以Ridge regression預測績效較佳，不論是在預設參數或是相對最佳參數組合，相對地Linear regression與SVR的預測績效則較差。在以預設參數執行預測的績效領先群模型中，進一步使用Grid search找出相對之最佳參數組合來執行預測評估，由於最佳參數組合是以MAE為評估指標，因此各模型MAE值皆比預設參數好，RMSE值亦多有改善，然而少數模型的預測績效並未改善或改善程度有限或無太大差異，例如GBR與DTR模型，顯然該模型的穩定性不適合於本研究個案的資料集，並且搜尋模型最佳參數在本個案的研究中相當的耗時。另外在模型訓練資料增加成為兩年度來預測下一年度時，其預測錯誤率會上升，例外情況是在銷售數量預測上，僅有ANN的預測績效更佳。

摘要(英)

Under the trend of fast fashion in the apparel industry, the needs of end customers are often quite uncertain. The business model of the garment manufacturing industry in the middle and lower reaches of the textile industry chain is mostly B2B. The customers are usually international fashion brand retailers such as GAP, H&M,ZARA, etc. In order to reduce costs and risks, retailers mostly use a small number of different orders with short lead times. The garment manufacturing industry needs to cooperate with customers to respond quickly and collaboratively. However, under the bullwhip effect of the supply chain, inventory Cost is one of key factors that affect profit directly. Therefore, it is necessary to be more sensitive to market demand. The accuracy of sales forecasts will be the key to improving profitability and rapid response. Production and demand planning can be optimized to make the operation of the supply chain more efficient. It is efficient and fast, and reduces waste and saves costs.
This study takes a domestically listed garment manufacturing supplier as an example. Its sales forecast relies on the integration of manual sales forecasts by business personnel based on subjective experience, past customer sales-related
data and order transparency and other information. However, the sales history is big data. There are no good big data analysis tools to assist in forecasting. This study conducted a preliminary comparison of machine model prediction performance. The experimental results show that the prediction performance of each data set in this case study,ridge regression model is better than others. Whether it is in the default parameters or the relatively best combination of parameters. Linear regression and SVR have poor predictive performance. In the performance leading group models with default parameters,that further execute prediction after using Grid search to find the relative best hyper parameters , due to the best parameter combination uses MAE as the evaluation index, the MAE value of each model is better than expected.Many models’ RMSE value has also improved. However, the prediction performance of a few models has not improved or the degree of improvement is limited or not much different, such as the GBR and DTR models. Obviously, the stability of these models is not suitable for the data set of this research case. And searching for the best hyper parameters of the model is quite time-consuming in this case study. In addition, when the model training data is increased into two years to predict the next year, its prediction error rate will increase. The exception is that only ANN′s prediction performance is better.

關鍵字(中)

★ B2B銷售預測
★ 機器學習
★ 回歸模型
★ 模型績效比較

關鍵字(英)

★ B2B sales forecasting
★ Machine learning
★ Regression model
★ Model performance comparison

論文目次

摘要 I
ABSTRACT II
目錄 III
圖目錄 IV
表目錄 V
第一章緒論 1
1.1 研究背景與動機 1
1.2 研究目的 2
1.3 論文架構 3
第二章文獻探討 4
2.1 銷售利潤與預測 4
2.2 機器學習技術 5
2.3 相關文獻回顧與討論 9
第三章研究方法 11
3.1 研究架構 11
3.2 資料前處理 12
3.3 建立機器學習模型 14
3.4 機器學習模型應用 15
第四章研究結果 21
4.1 資料描述 21
4.2 機器學習模型評選 22
4.3 最佳模型之參數最佳化分析 25
4.4 資料量之預測績效影響分析 33
第五章結論與建議 35
5.1 結論 35
5.2 未來研究建議 36
參考文獻 37

參考文獻

參考文獻
[1] “紡織業概況 - 產業資訊 - 經濟部工業局民生領域相關計畫.” https://www.tipo.org.tw/tc/about_textile_2.aspx (accessed May 10, 2021).
[2] “mgi-artificial-intelligence-discussion-paper.pdf.” Accessed: Mar. 31, 2021. [Online]. Available: https://www.mckinsey.com/~/media/mckinsey/industries/advanced%20electronics/our%20insights/how%20artificial%20intelligence%20can%20deliver%20real%20value%20to%20companies/mgi-artificial-intelligence-discussion-paper.ashx
[3] “報1 經濟部提升紡織產業競爭優勢措施(M).pdf.”
[4] “102年度臺灣製MIT微笑產品生產工廠品質管理系統建置指引_衣服類產業.pdf.”
[5] T. Boone, R. Ganeshan, A. Jain, and N. R. Sanders, “Forecasting sales in the supply chain: Consumer analytics in the big data era,” Int. J. Forecast., vol. 35, no. 1, pp. 170–180, Jan. 2019, doi: 10.1016/j.ijforecast.2018.09.003.
[6] G. L. Lilien, “The B2B Knowledge Gap,” Int. J. Res. Mark., vol. 33, no. 3, pp. 543–556, Sep. 2016, doi: 10.1016/j.ijresmar.2016.01.003.
[7] “特力集團—全方位貿易服務 - 光華管理個案收錄庫.” https://www.kmcc.org.tw/admin/case/upload/predis_pdf (accessed May 10, 2021).
[8] M. Bohanec, M. K. Borštnar, and M. Robnik-Šikonja, “Integration of Machine Learning Insights into Organizational Learning: A Case of B2B Sales Forecasting,” in Blurring the Boundaries Through Digital Innovation, Cham, 2016, pp. 71–85. doi: 10.1007/978-3-319-38974-5_7.
[9] D. F. Davis and J. T. Mentzer, “Organizational factors in sales forecasting management,” Int. J. Forecast., vol. 23, no. 3, pp. 475–495, Jul. 2007, doi: 10.1016/j.ijforecast.2007.02.005.
[10] M. Bohanec, M. Robnik-Šikonja, and M. Kljajić Borštnar, “Organizational Learning Supported by Machine Learning Models Coupled with General Explanation Methods: A Case of B2B Sales Forecasting,” Organizacija, vol. 50, no. 3, Art. no. 3, Jan. 2017, Accessed: May 03, 2021. [Online]. Available: http://organizacija.fov.uni-mb.si/index.php/organizacija/article/view/780
[11] X. Xu, L. Tang, and V. Rangan, “Hitting your number or not? A robust intelligent sales forecast system,” in 2017 IEEE International Conference on Big Data (Big Data), Dec. 2017, pp. 3613–3622. doi: 10.1109/BigData.2017.8258355.
[12] B. Suh, “Sales Teams Aren’t Great at Forecasting. Here’s How to Fix That.,” Harvard Business Review, Mar. 19, 2019. Accessed: May 04, 2021. [Online]. Available: https://hbr.org/2019/03/sales-teams-arent-great-at-forecasting-heres-how-to-fix-that
[13] F. Provost and T. Fawcett, “Data Science and its Relationship to Big Data and Data-Driven Decision Making,” Big Data, vol. 1, no. 1, pp. 51–59, Feb. 2013, doi: 10.1089/big.2013.1508.
[14] E. Brynjolfsson, L. M. Hitt, and H. H. Kim, “Strength in Numbers: How Does Data-Driven Decisionmaking Affect Firm Performance?,” Social Science Research Network, Rochester, NY, SSRN Scholarly Paper ID 1819486, Apr. 2011. doi: 10.2139/ssrn.1819486.
[15] A. McAfee and E. Brynjolfsson, “Big Data: The Management Revolution,” Harvard Business Review, Oct. 01, 2012. Accessed: May 04, 2021. [Online]. Available: https://hbr.org/2012/10/big-data-the-management-revolution
[16] E. W. T. Ngai, S. Peng, P. Alexander, and K. K. L. Moon, “Decision support and intelligent systems in the textile and apparel supply chain: An academic review of research articles,” Expert Syst. Appl., vol. 41, no. 1, pp. 81–91, Jan. 2014, doi: 10.1016/j.eswa.2013.07.013.
[17] A. L. D. Loureiro, V. L. Miguéis, and L. F. M. da Silva, “Exploring the use of deep neural networks for sales forecasting in fashion retail,” Decis. Support Syst., vol. 114, pp. 81–93, Oct. 2018, doi: 10.1016/j.dss.2018.08.010.
[18] “Machine Learning Made Easy: A Review of Scikit-learn Package in Python Programming Language - Jiangang Hao, Tin Kam Ho, 2019.” https://journals.sagepub.com/doi/abs/10.3102/1076998619832248 (accessed May 18, 2021).
[19] F. Halili and A. Rustemi, “Predictive Modeling : Data Mining Regression Technique Applied in a Prototype 1,” 2016. /paper/Predictive-Modeling-%3A-Data-Mining-Regression-in-a-1-Halili-Rustemi/a9ff9f770393b9b1b49aeed9ed3ffc6586ddcceb (accessed May 06, 2021).
[20] T.-M. Choi, C.-L. Hui, N. Liu, S.-F. Ng, and Y. Yu, “Fast fashion sales forecasting with limited data and time,” Decis. Support Syst., vol. 59, pp. 84–92, Mar. 2014, doi: 10.1016/j.dss.2013.10.008.
[21] A. L. D. Loureiro, V. L. Miguéis, and L. F. M. da Silva, “Exploring the use of deep neural networks for sales forecasting in fashion retail,” Decis. Support Syst., vol. 114, pp. 81–93, Oct. 2018, doi: 10.1016/j.dss.2018.08.010.
[22] T.-M. Choi, C.-L. Hui, N. Liu, S.-F. Ng, and Y. Yu, “Fast fashion sales forecasting with limited data and time,” Decis. Support Syst., vol. 59, pp. 84–92, Mar. 2014, doi: 10.1016/j.dss.2013.10.008.
[23] S. Thomassey and M. Happiette, “A neural clustering and classification system for sales forecasting of new apparel items,” Appl. Soft Comput., vol. 7, no. 4, pp. 1177–1187, Aug. 2007, doi: 10.1016/j.asoc.2006.01.005.
[24] Y. Yu, T.-M. Choi, and C.-L. Hui, “An intelligent fast sales forecasting model for fashion products,” Expert Syst. Appl., vol. 38, no. 6, pp. 7373–7379, Jun. 2011, doi: 10.1016/j.eswa.2010.12.089.
[25] A. Fallah Tehrani and D. Ahrens, “Enhanced predictive models for purchasing in the fashion field by using kernel machine regression equipped with ordinal logistic regression,” J. Retail. Consum. Serv., vol. 32, pp. 131–138, Sep. 2016, doi: 10.1016/j.jretconser.2016.05.008.
[26] A. Rezazadeh, “A Generalized Flow for B2B Sales Predictive Modeling: An Azure Machine Learning Approach,” ArXiv, 2020, doi: 10.3390/FORECAST2030015.
[27] “Approach and Solution to break in Top 20 of Big Mart Sales prediction,” Analytics Vidhya, Feb. 11, 2016. https://www.analyticsvidhya.com/blog/2016/02/bigmart-sales-solution-top-20/ (accessed Jun. 08, 2021).
[28] C. Willmott and K. Matsuura, “Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,” 2005, doi: 10.3354/CR030079.
[29] T. Chai and R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)?,” Geosci Model Dev, vol. 7, Jan. 2014, doi: 10.5194/gmdd-7-1525-2014.
[30] M. Kuhn and K. Johnson, “Linear Regression and Its Cousins,” in Applied Predictive Modeling, M. Kuhn and K. Johnson, Eds. New York, NY: Springer, 2013, pp. 101–139. doi: 10.1007/978-1-4614-6849-3_6.
[31] S. K. Prion and K. A. Haerling, “Making Sense of Methods and Measurements: Simple Linear Regression,” Clin. Simul. Nurs., vol. 48, pp. 94–95, Nov. 2020, doi: 10.1016/j.ecns.2020.07.004.
[32] M. Budka and B. Gabrys, “Ridge regression ensemble for toxicity prediction,” Procedia Comput. Sci., vol. 1, no. 1, pp. 193–201, May 2010, doi: 10.1016/j.procs.2010.04.022.
[33] R. A. Willoughby, “Solutions of Ill-Posed Problems (A. N. Tikhonov and V. Y. Arsenin),” SIAM Rev., vol. 21, no. 2, pp. 266–267, Apr. 1979, doi: 10.1137/1021044.
[34] “迴歸分析中共線性於Suppression與Collapsibility之效果探討__臺灣博碩士論文知識加值系統.” https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22107NCCU5337016%22.&searchmode=basic (accessed May 19, 2021).
[35] “Introduction to Data Mining.” https://www-users.cs.umn.edu/~kumar001/dmbook/index.php (accessed May 19, 2021).
[36] L. Rokach and O. Maimon, “Decision Trees,” in Data Mining and Knowledge Discovery Handbook, O. Maimon and L. Rokach, Eds. Boston, MA: Springer US, 2005, pp. 165–192. doi: 10.1007/0-387-25465-X_9.
[37] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
[38] “Random forest regression prediction of solid particle Erosion in elbows - ScienceDirect.” https://www.sciencedirect.com/science/article/abs/pii/S0032591018305539 (accessed May 21, 2021).
[39] D. M. Hawkins, “The Problem of Overfitting,” J. Chem. Inf. Comput. Sci., vol. 44, no. 1, pp. 1–12, Jan. 2004, doi: 10.1021/ci0342472.
[40] C.-H. Wang and Y. Yun, “Demand planning and sales forecasting for motherboard manufacturers considering dynamic interactions of computer products,” Comput. Ind. Eng., vol. 149, p. 106788, Nov. 2020, doi: 10.1016/j.cie.2020.106788.
[41] “SVR mathematical model and methods for sale prediction - ScienceDirect.” https://www.sciencedirect.com/science/article/abs/pii/S1004413208600183 (accessed May 17, 2021).
[42] “電腦代理商銷售預測模式之建構－多種資料探勘技術之應用與比較__臺灣博碩士論文知識加值系統.” https://ndltd.ncl.edu.tw/cgi-bin/gs32/gsweb.cgi/login?o=dnclcdr&s=id=%22098FJU00457056%22.&searchmode=basic (accessed May 17, 2021).
[43] A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Stat. Comput., vol. 14, no. 3, pp. 199–222, Aug. 2004, doi: 10.1023/B:STCO.0000035301.49549.88.
[44] J. Cai, K. Xu, Y. Zhu, F. Hu, and L. Li, “Prediction and analysis of net ecosystem carbon exchange based on gradient boosting regression and random forest,” Appl. Energy, vol. 262, p. 114566, Mar. 2020, doi: 10.1016/j.apenergy.2020.114566.
[45] P. Prettenhofer and G. Louppe, “Gradient Boosted Regression Trees,” p. 39.
[46] S. Ben Taieb and R. J. Hyndman, “A gradient boosting approach to the Kaggle load forecasting competition,” Int. J. Forecast., vol. 30, no. 2, pp. 382–394, Apr. 2014, doi: 10.1016/j.ijforecast.2013.07.005.
[47] H. D. Nguyen, G. T. Truong, and M. Shin, “Development of extreme gradient boosting model for prediction of punching shear resistance of r/c interior slabs,” Eng. Struct., vol. 235, p. 112067, May 2021, doi: 10.1016/j.engstruct.2021.112067.
[48] G. Ke et al., “LightGBM: a highly efficient gradient boosting decision tree,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, Red Hook, NY, USA, Dec. 2017, pp. 3149–3157.
[49] J. Fan, X. Ma, L. Wu, F. Zhang, X. Yu, and W. Zeng, “Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data,” Agric. Water Manag., vol. 225, p. 105758, Nov. 2019, doi: 10.1016/j.agwat.2019.105758.
[50] J. Brownlee, “Hyperparameter Optimization With Random Search and Grid Search,” Machine Learning Mastery, Sep. 13, 2020. https://machinelearningmastery.com/hyperparameter-optimization-with-random-search-and-grid-search/ (accessed Mar. 16, 2021).
[51] “The-Morgan-Kaufmann-Series-in-Data-Management-Systems-Jiawei-Han-Micheline-Kamber-Jian-Pei-Data-Mining.-Concepts-and-Techniques-3rd-Edition-Morgan-Kaufmann-2011.pdf.” Accessed: May 20, 2021. [Online]. Available: http://myweb.sabanciuniv.edu/rdehkharghani/files/2016/02/The-Morgan-Kaufmann-Series-in-Data-Management-Systems-Jiawei-Han-Micheline-Kamber-Jian-Pei-Data-Mining.-Concepts-and-Techniques-3rd-Edition-Morgan-Kaufmann-2011.pdf
[52] D. Veit, “2 - Neural networks and their application to textile technology,” in Simulation in Textile Technology, D. Veit, Ed. Woodhead Publishing, 2012, pp. 9–71. doi: 10.1533/9780857097088.9.
[53] C. Bircanoğlu and N. Arıca, “A comparison of activation functions in artificial neural networks,” in 2018 26th Signal Processing and Communications Applications Conference (SIU), May 2018, pp. 1–4. doi: 10.1109/SIU.2018.8404724.
[54] Q. Huang, J. Mao, and Y. Liu, “An improved grid search algorithm of SVR parameters optimization,” in 2012 IEEE 14th International Conference on Communication Technology, Nov. 2012, pp. 1022–1026. doi: 10.1109/ICCT.2012.6511415.

指導教授

蔡志豐

審核日期

2021-7-22

推文