近年來，現代消費者需求變化快速，同業間競爭越來越激烈，企業為了保持競爭力並滿足消費者需求，需不斷開發使產品快速推陳出新，然而，隨著產品種類的增加及銷售數量劇增，庫存數量的預測也會變得越來越複雜。容易造成庫存數量難以控制，如果庫存量過多會導致企業資源以及資金的浪費；庫存量過少則會造成客戶不滿意，第一線銷售人員做銷售時容易因為缺貨疲於與顧客解釋造成壓力而影響業績。歷史文獻大部分利用機器學習透過探討產品數量預測需求改善庫存數量，而本研究除了針對產品數量並探討其他多個變因影響庫存數量的變化，並找出變因與案例庫存數量之關係。
本研究以現有實際案例的庫存數量、訂單數量、銷售數量、採購數量以及淡季旺季等數據為基礎，進行庫存數量與這些因素之間的關係分析。本研究採用機器學習技術，採用長短期記憶模型，探討這些因素對庫存數量的影響。透過分析庫存數量、訂單數量、銷售數量、採購數量以及淡季旺季，找出之間的相互關係和趨勢，並且驗證其準確性。

In recent years, the swift changes in modern consumer demands and the intensifying competition within industries have driven businesses to consistently innovate and launch new products to maintain their competitive edge and fulfill customer needs. However, with the diversification and dramatic increase in product sales, the prediction of inventory quantities becomes increasingly complex, leading to potential difficulties in managing stock levels. Having excess inventory can lead to wastage of resources and capital, while insufficient stock can result in customer dissatisfaction and stress for frontline sales staff, thereby affecting performance. Most historical literature has employed machine learning to explore product quantity prediction to improve inventory management. This research, in addition to focusing on product quantity, also investigates other multiple factors influencing inventory variation and identifies the correlation between these factors and case inventory quantities.
Based on the existing real-case data of inventory quantities, order quantities, sales quantities, procurement quantities, as well as off-peak and peak season data, this study analyzes the relationships between these factors and inventory quantities. We utilize machine learning techniques to investigate these factors' impact on inventory quantities. By examining inventory, order, sales, procurement quantities, and off-peak and peak seasons, we identify interrelationships, trends, and validate their accuracy.

論文審定書i
致謝ii
摘要iii
Abstractiv
目錄v
圖次vii
表次viii
第一章 緒論1
1.1研究背景1
1.2研究動機3
1.3研究目的4
第二章 文獻探討5
2.1 類神經網路5
2.2 深度學習6
2.3 前饋式類神經網路7
2.4 倒傳遞類神經網路7
2.5 遞迴類神經網路8
2.6 長短期記憶模型10
第三章 研究方法12
3.1 研究架構12
3.2資料來源收集14
3.3資料前處理15
3.3.1 內插法15
3.3.2 正規化15
3.3.3 分割訓練集、測試集15
3.4預測模型15
第四章 研究結果與分析17
4.1基於統計分析之需求預測17
4.2效能評估17
4.3 LSTM預測模型18
4.3.1設定記憶長度之預測結果19
4.3.2 LSTM參數調整20
4.3.3 與其他模型比較23
第五章 討論與建議25
5.1 研究結論25
5.2 研究建議25
第六章 參考文獻26

[1] G. Hsia, "吃掉企業獲利的兇手：產品經理該如何做好「庫存管理」," 2016. [Online]. Available: https://www.pmtone.com/inventory-management-for-a-pm/.
[2] S. I. Inc., "讓 AI 入魂，精準預測你的需求與庫存！," p. 1, 2019. [Online]. Available: https://buzzorange.com/techorange/2019/02/13/ai-predict-demand-and-inventory/.
[3] 潘亮晴, "基於財經字典與分析指標的神經網路預測股價趨勢," 碩士, 資訊工程學系, 逢甲大學, 台中市, 2022. [Online]. Available: https://hdl.handle.net/11296/6e3vnn
[4] 許澤林, "類神經網路預測股價走勢," 碩士, 應用數學所, 逢甲大學, 台中市, 2012. [Online]. Available: https://hdl.handle.net/11296/degchu
[5] 馬偉翔, "用人工神經網路預測股價走勢," 碩士, 財務金融碩士在職專班, 國立清華大學, 新竹市, 2019. [Online]. Available: https://hdl.handle.net/11296/m8spfs
[6] 李欣海, "随机森林模型在分类与回归分析中的应用," 2013.
[7] 楊雅媛, "迴歸分析與類神經網路預測能力之比較," 碩士, 統計學系, 國立政治大學, 台北市, 2002. [Online]. Available: https://hdl.handle.net/11296/9tzcj8
[8] 蔡怡佳, "應用類神經網路技術達到需求驅動物料需求預測 -以生產使用耗材為例," 碩士, 資訊管理系, 國立雲林科技大學, 雲林縣, 2023. [Online]. Available: https://hdl.handle.net/11296/fj6m36
[9] 鄧光廷, "運用倒傳遞類神經網路對最小存貨成本需求預測研究—以零售商（機車保養）為例," 碩士, 資訊應用學系, 佛光大學, 宜蘭縣, 2016. [Online]. Available: https://hdl.handle.net/11296/a7gg6n
[10] 李季翰, "應用灰關聯分析與類神經網路訓練於軟式IC載板生產預測之研究," 碩士, 工業管理學系碩士在職專班, 義守大學, 高雄市, 2013. [Online]. Available: https://hdl.handle.net/11296/x5d965
[11] J. Yim, "A comparison of neural networks with time series models for forecasting returns on a stock market index," in Developments in Applied Artificial Intelligence: 15th International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems IEA/AIE 2002 Cairns, Australia, June 17–20, 2002 Proceedings 15, 2002: Springer, pp. 25-35.
[12] 楊金聲, "利用類神經網路與線性迴歸進行成本預測之研究-以印刷電路板產業為例," 碩士, 資訊管理研究所, 中原大學, 桃園縣, 2005. [Online]. Available: https://hdl.handle.net/11296/k3w7ya
[13] 林東清, "資訊管理：e化企業的核心競爭能力," 2018, ch. 資訊管理的智慧觀點：技術篇, p. 121.
[14] D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning representations by back-propagating errors," nature, vol. 323, no. 6088, pp. 533-536, 1986.
[15] S. Mirjalili, S. Z. M. Hashim, and H. M. Sardroudi, "Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm," Applied Mathematics and Computation, vol. 218, no. 22, pp. 11125-11137, 2012.
[16] D. E. Rumelhart, G. E. Hinton, and J. L. McClelland, "A general framework for parallel distributed processing," Parallel distributed processing: Explorations in the microstructure of cognition, vol. 1, no. 45-76, p. 26, 1986.
[17] 蘭雪梅、朱健、黃承明、董德存, "BP 網絡的 MATLAB 實現，微型電腦應用," 2003.
[18] 夏文琪, "考慮循環趨勢應用人工智慧於期貨商品價格預測-以台指期貨為例," 碩士, 資訊管理學系碩士在職專班, 中國文化大學, 台北市, 2013. [Online]. Available: https://hdl.handle.net/11296/t96fnr
[19] 王翎聿, "應用倒傳遞類神經網路與支援向量機預測加權股價指數," 碩士, 財務管理學系, 國防大學, 桃園縣, 2015. [Online]. Available: https://hdl.handle.net/11296/8cqn86
[20] 高聿緯, "關聯式學習：利用自動編碼器與目標傳遞法分解端到端倒傳遞演算法," 碩士, 資訊工程學系, 國立中央大學, 桃園縣, 2019. [Online]. Available: https://hdl.handle.net/11296/azcv76
[21] 陳宏祥, "應用於存貨額預測之統計與類神經網路的比較研究," 碩士, 管理科學研究所, 淡江大學, 新北市, 2004. [Online]. Available: https://hdl.handle.net/11296/xuq763
[22] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities," Proceedings of the national academy of sciences, vol. 79, no. 8, pp. 2554-2558, 1982.
[23] M. Jordan, "Serial order: a parallel distributed processing approach. technical report, june 1985-march 1986," California Univ., San Diego, La Jolla (USA). Inst. for Cognitive Science, 1986.
[24] J. L. Elman, "Finding structure in time," Cognitive science, vol. 14, no. 2, pp. 179-211, 1990.
[25] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature, vol. 521, no. 7553, pp. 436-444, 2015.
[26] S. Hochreiter, "Untersuchungen zu dynamischen neuronalen Netzen," Diploma, Technische Universität München, vol. 91, no. 1, 1991.
[27] 陳雅昀, "基於RNN、LSTM、GRU模型之比較 -以電力需求預測為例," 碩士, 資訊管理學系, 元智大學, 桃園縣, 2020. [Online]. Available: https://hdl.handle.net/11296/k623m8
[28] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[29] A. Graves and J. Schmidhuber, "Offline handwriting recognition with multidimensional recurrent neural networks," Advances in neural information processing systems, vol. 21, 2008.
[30] M. S. Islam and E. Hossain, "Foreign exchange currency rate prediction using a GRU-LSTM hybrid network," Soft Computing Letters, vol. 3, p. 100009, 2021.
[31] J. Huang, W. Zhou, Q. Zhang, H. Li, and W. Li, "Video-based sign language recognition without temporal segmentation," in Proceedings of the AAAI Conference on Artificial Intelligence, 2018, vol. 32, no. 1.
[32] 陳煜文, "以委託單資料預測當日股價趨勢－LSTM類神經網路模型之應用," 碩士, 金融與國際企業學系金融碩士班, 輔仁大學, 新北市, 2018. [Online]. Available: https://hdl.handle.net/11296/e4fk26
[33] 許哲昇, "使用長短期記憶深度學習 之機器剩餘可用壽命預估," 碩士, 資訊工程學系, 國立中央大學, 桃園縣, 2017. [Online]. Available: https://hdl.handle.net/11296/7er8xs
[34] A. Graves, M. Liwicki, S. Fernández, R. Bertolami, H. Bunke, and J. Schmidhuber, "A novel connectionist system for unconstrained handwriting recognition," IEEE transactions on pattern analysis and machine intelligence, vol. 31, no. 5, pp. 855-868, 2008.
[35] A. L. Ellefsen, E. Bjørlykhaug, V. Æsøy, S. Ushakov, and H. Zhang, "Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture," Reliability Engineering & System Safety, vol. 183, pp. 240-251, 2019.
[36] J.-D. Kim, J.-G. Lee, and S. W. Han, "Evaluation of long short-term memory versus recurrent neural networks for demand forecasting in supply chains," 2023.
[37] 羅婉甄, "運用長短期記憶網路演算法建構公部門船用油料庫儲需求量預測模型," 碩士, 運籌管理學系, 國防大學, 桃園縣, 2020. [Online]. Available: https://hdl.handle.net/11296/m34zn2
[38] 余桂霖, 時間序列分析. 台灣五南圖書出版股份有限公司, 2013.