政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/156059
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 114895/145933 (79%)
造訪人次 : 53867808      線上人數 : 733
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋
    政大機構典藏 > 商學院 > 資訊管理學系 > 學位論文 >  Item 140.119/156059


    請使用永久網址來引用或連結此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/156059


    題名: 演算法定價與雙目標深度學習
    Algorithmic Pricing and Dual-Objective Deep Learning
    作者: 林子紘
    Lin, Zi-Hong
    貢獻者: 莊皓鈞
    周彥君
    Chuang, Hao-Chun
    Chou, Yen-Chun
    林子紘
    Lin, Zi-Hong
    關鍵詞: 動態定價
    客製化損失函數
    神經網路定價
    Dynamic Pricing
    Customized Loss Function
    Neural Network Pricing
    日期: 2024
    上傳時間: 2025-03-03 15:10:15 (UTC+8)
    摘要: 動態定價被視為最基本與最常用的收益管理工具之一，過往具有許多不同層面的研究。隨著網路科技的發展，動態定價研究在取得消費者資訊和調整價格成本方面的進步，動態定價運用在個人化定價的應用也越來越廣泛，能提供消費者更適合的價格，從而提高整體收益。然而，準確了解消費者需求並推薦合適價格是一項挑戰，但隨著新技術的發展，透過機器學習與深度學習可以更全面地且更精準地進行動態定價。

    本研究首先比較了兩種主要的動態定價方法：兩階段模型和客製化損失函數。我們使用實證資料以及模擬資料進行比較及分析，並提出一改良的損失函數——Dynamic Airbnb Loss，與其他方法進行比較，證實了該損失函數在參數設定上更直觀且效果更佳的優勢。

    本研究之另一重點為根據消費者的價值評估函數理論基礎發想，提出了一雙目標之神經網路模型。我們利用神經網路的彈性設計優勢，透過同時預測價格以及該價格之購買機率的方法，並且加入神經網路正規化概念，藉此能夠推薦接近消費者最大願付價格的價格。我們將此架構運用在模擬資料中，透過獲利以及不同的評估指標，證實我們所提出的雙目標神經網路是具有可行性也具有相當的潛力。
    Dynamic pricing is regarded as one of the most fundamental revenue management tools, with extensive research from various perspectives. With advancements in technology, dynamic pricing research has made significant progress in obtaining consumer information and reducing price adjustment costs. Personalized pricing applications of dynamic pricing are becoming widespread, offering consumers more suitable prices and enhancing overall revenue. However, accurately understanding consumer demand and recommending appropriate prices is challenging. Machine learning and deep learning enable more comprehensive and precise dynamic pricing.

    This research compares two main dynamic pricing methods: the two-stage model and the model using a customized loss function. We conduct analysis using empirical and simulated data and propose an improved loss function, the Dynamic Airbnb Loss. Compared to other methods, this new loss function demonstrates advantages in being more intuitive in parameter settings and more effective in application.

    Another key focus of this research is a dual-objective neural network model based on the theoretical foundation of consumer value assessment functions. Leveraging the flexibility of neural network design, we simultaneously predict prices and the probability of purchase at those prices with the concept of neural network regularization. This approach allows us to recommend prices that are close to the consumer’s maximum willingness to pay. We apply this framework to simulated data and evaluate it through profitability and various performance metrics, confirming that the proposed dual-objective neural network is both feasible and highly promising.
    參考文獻: Amram, M., Dunn, J., & Zhuo, Y. D. (2022). Optimal policy trees. Machine Learning, 111(7), 2741–2768.
    Bajari, P., Nekipelov, D., Ryan, S. P., & Yang, M. (2015). Demand estimation with machine learning and model combination (tech. rep.). National Bureau of Economic Research.
    Banerjee, S., Johari, R., & Riquelme, C. (2016). Dynamic pricing in ridesharing platforms. ACM SIGecom Exchanges, 15(1), 65–70.
    Bayoumi, A. E.-M., Saleh, M., Atiya, A. F., & Aziz, H. A. (2013). Dynamic pricing for hotel revenue management using price multipliers. Journal of Revenue and Pricing Management, 12, 271–285.
    Berry, S. T., & Haile, P. A. (2021). Foundations of demand estimation. In Handbook of Industrial Organization (Vol. 4, pp. 1–62). Elsevier.
    Biggs, M. (2022). Convex surrogate loss functions for contextual pricing with transaction data. arXiv preprint arXiv:2202.10944.
    Biggs, M., Sun, W., & Ettl, M. (2021). Model distillation for revenue optimization: Interpretable personalized pricing. International Conference on Machine Learning, 946–956.
    Bitran, G., & Caldentey, R. (2003). An overview of pricing models for revenue management. Manufacturing & Service Operations Management, 5(3), 203–229.
    Chen, M., & Chen, Z.-L. (2015). Recent developments in dynamic pricing research: Multiple products, competition, and limited demand information. Production and Operations Management, 24(5), 704–731.
    Chen, N., Lagzi, S., & Milner, J. (2022). Using neural networks to guide data-driven operational decisions. Available at SSRN 4217092.
    Den Boer, A. V. (2015). Dynamic pricing and learning: Historical origins, current research, and new directions. Surveys in Operations Research and Management Science, 20(1), 1–18.
    Elmaghraby, W., & Keskinocak, P. (2003). Dynamic pricing in the presence of inventory considerations: Research overview, current practices, and future directions. Management Science, 49(10), 1287–1309.
    Hawkins, E. R. (1957). Methods of estimating demand. Journal of Marketing, 21(4), 428–438.
    Kolbeinsson, A., Shukla, N., Gupta, A., Marla, L., & Yellepeddi, K. (2022). Galactic air improves ancillary revenues with dynamic personalized pricing. INFORMS Journal on Applied Analytics, 52(3), 233–249.
    Lin, K. Y. (2006). Dynamic pricing with real-time demand learning. European Journal of Operational Research, 174(1), 522–538.
    Pereyra, G., Tucker, G., Chorowski, J., Kaiser, Ł., & Hinton, G. (2017). Regularizing neural networks by penalizing confident output distributions. arXiv preprint arXiv:1701.06548.
    Rosenbaum, P. R., & Rubin, D. B. (1983). The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1), 41–55.
    Thirumuruganathan, S., Al Emadi, N., Jung, S.-g., Salminen, J., Robillos, D. R., & Jansen, B. J. (2023). Will they take this offer? A machine learning price elasticity model for predicting upselling acceptance of premium airline seating. Information & Management, 60(3), 103759.
    Weiss, R. M., & Mehrotra, A. K. (2001). Online dynamic pricing: Efficiency, equity, and the future of e-commerce. Va. JL & Tech., 6, 1.
    Ye, P., Qian, J., Chen, J., Wu, C.-h., Zhou, Y., De Mars, S., Yang, F., & Zhang, L. (2018). Customized regression model for Airbnb dynamic pricing. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 932–940.
    Yin, C., & Han, J. (2021). Dynamic pricing model of e-commerce platforms based on deep reinforcement learning. CMES-Computer Modeling in Engineering & Sciences, 127(1).
    描述: 碩士
    國立政治大學
    資訊管理學系
    111356014
    資料來源: http://thesis.lib.nccu.edu.tw/record/#G0111356014
    資料類型: thesis
    顯示於類別:[資訊管理學系] 學位論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    601401.pdf1661KbAdobe PDF0檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋