Responsive image
博碩士論文 etd-0815121-074738 詳細資訊
Title page for etd-0815121-074738
論文名稱
Title
多模態零售商店存活機率評估方法 –以四大超商為例
Multi-modal method for survival probability Evaluation – A Case Study of four Convenience stores
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
57
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2021-07-28
繳交日期
Date of Submission
2021-09-15
關鍵字
Keywords
商圈評估、機器學習、遷移學習、多模態學習、特徵萃取
business circle evaluation, machine learning, transfer learning, multi-modal learning, Feature extraction
統計
Statistics
本論文已被瀏覽 394 次,被下載 0
The thesis/dissertation has been browsed 394 times, has been downloaded 0 times.
中文摘要
過去商圈評估通常需要藉由人力收集交通、租金、所得,與周邊相關同業經營狀況, 來估計商店在此商圈的存活機率。本研究使用地理資訊資料(政府公開資料)並結合影像 (Google 街景),使用多模態機器學習模型(Multi-modal Machine Learning Models)對 商店在此商圈的存活機率作出預測。 除了參考過去商圈評估研究的問卷變項之外,我 們額外收集、製作相關變數、並且收集 Google 街景圖、使用人工智慧方法從圖像中抽 取街景特徵,並透過隨機森林建立預測性模型,欲驗證是否加入圖像能改善模型的辨識 能力。我們發現加入街景圖像特徵可使得預測的準確度提高。過去此領域學者主要以問 卷方法評估超商存活,通常以小範圍為主,且通常曠日費時。本研究發現同業超商的分 佈以統一超、全家影響最明顯,當地的電子發票消費情況,星巴克以及租金皆是影響超 商存活的主要原因,而交通設施的影響性較低。對零售業集團與加盟業者,本研究所提 出的方法可望降低評估商圈的時間以及人力成本。
Abstract
In the past, business district evaluation usually required manpower. They collected traffic, rent, income to estimate the survival rate of convenience store. In my research, we combine geographic data with images from google street view. Then we use the multi-modal machine learning model to solve this problem.
We collect more columns of data than the past, and we use transfer learning to extract image features from street view data, and then we use machine learning to build model. We have to verify whether adding image features would boost model performance.
We found that adding street view features can boost the accuracy of whether convenience store would survive. In the past, scholars in this field mainly used questionnaires to estimate the survival of convenience stores, but they usually do it in a small area, and spend lots of time. We use big data method by multi-modal learning and transfer learning,which cost us less time. By means of this method, we could quickly copy to other industries.
We found that survival rate of convenience store are affected by the distribution of four convenience stores, e-invoice, Starbucks, rent etc. However, we found traffic factors are less important to convenience store. The benefits of this research are not only for retail franchisees, but also reduce the time and labor costs for pre-evaluating business circles.
目次 Table of Contents
目錄
論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 vii
表次 viii
第一章 緒論1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 論文架構 3
第二章 文獻探討與整理4
第一節 過往商圈評估研究方法 4
第二節 零售商圈理論 7
第三節 機器學習方法 8
第四節 遷移學習(TRANSFER LEARNING) 10
第五節 多模態學習(MULTIMODAL-LEARNING) 13
第三章 研究方法15
第一節 研究方法流程 15
第二節 超商模態處理 17
第三節 街景模態處理 25
第四節 建立多模態模型 28
第四章 資料分析30
第一節 評估標準 30
第二節 分析結果 31
第三節 變數重要性 35
第五章 結論與建議39
第一節 研究結果與貢獻 39
第二節 研究限制與未來建議 40
參考文獻43
參考文獻 References
Dietterich, T. G. (2002). Ensemble learning. The Handbook of Brain Theory and Neural Networks, 2, 110–125.
Gebru, T., Krause, J., Wang, Y., Chen, D., Deng, J., Aiden, E. L., & Fei-Fei, L. (2017). Using deep learning and Google Street View to estimate the demographic makeup of neighborhoods across the United States. Proceedings of the National Academy of Sciences, 114(50), 13108–13113.
Skinner, D., Nelson, R. R., Chin, W., & Land, L. (2015). The Delphi Method Research Strategy in Studies of Information Systems. Communications of the Association for Information Systems, 37, 31–63.
Zeileis, A., Hothorn, T., & Hornik, K. (2008). Model-Based Recursive Partitioning. Journal of Computational and Graphical Statistics, 17(2), 492–514.
Huff, D. L. (1964). Defining and Estimating a Trading Area. Journal of Marketing, 28(3), 34–38.
Roig-Tierno, N., Baviera-Puig, A., Buitrago-Vera, J., & Verdú, F. (2013). The retail site location decision process using GIS and the analytical hierarchy process. Applied Geography, 40, 191–198.
Nevin, J. A. (1969). SIGNAL DETECTION THEORY AND OPERANT BEHAVIOR: A Review of David M. Green and John A. Swets’ Signal Detection Theory and Psychophysics.1. Journal of the Experimental Analysis of Behavior, 12(3), 475–480.
Zweig, M. H., & Campbell, G. (1993). Receiver-operating characteristic (ROC) plots: A fundamental evaluation tool in clinical medicine. Clinical Chemistry, 39(4), 561–577.
Turhan, G. (2013). The application of AHP approach for evaluating location selection elements for retail store: A case of clothing store. International Journal of Research in Business and Social Science, 2, 1–20.
Altmann, A., Toloşi, L., Sander, O., & Lengauer, T. (2010). Permutation importance: A corrected feature importance measure. Bioinformatics, 26(10), 1340–1347.
Aryafar, K., Guillory, D., & Hong, L. (2017). An Ensemble-based Approach to Click- Through Rate Prediction for Promoted Listings at Etsy. Proceedings of the ADKDD’17, 1–6.
Baltrušaitis, T., Ahuja, C., & Morency, L.-P. (2017). Multimodal Machine Learning: A Survey and Taxonomy. ArXiv:1705.09406 [Cs].
Breiman, L. (2001a). Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author). Statistical Science, 16(3), 199–231.
Breiman, L. (2001b). Random Forests. Machine Learning, 45(1), 5–32.
Dalkey, N., & Helmer, O. (1963). An Experimental Application of the DELPHI Method to
the Use of Experts. Management Science, 9(3), 458–467.
Guo, G., Wang, H., Bell, D., Bi, Y., & Greer, K. (2003). KNN Model-Based Approach in
Classification. In R. Meersman, Z. Tari, & D. C. Schmidt (Eds.), On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE (pp. 986–996). Springer.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. ArXiv:1512.03385 [Cs].
Heaton, J. (2018). Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning. Genetic Programming and Evolvable Machines, 19(1), 305–307.
Huff, D. L. (1964). Defining and Estimating a Trading Area. Journal of Marketing, 28(3), 34–38.
Izenman, A. J. (2008). Linear Discriminant Analysis. In A. J. Izenman (Ed.), Modern Multivariate Statistical Techniques: Regression, Classification, and Manifold Learning (pp. 237–280). Springer.
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., Hughes, M., & Dean, J. (2017). Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. Transactions of the Association for Computational Linguistics, 5, 339–351.
Kuo, R. J., Chi, S. C., & Kao, S. S. (2002). A decision support system for selecting convenience store location through integration of fuzzy AHP and artificial neural network. Computers in Industry, 47, 199–214.
Liu, R., Shi, Y., Ji, C., & Jia, M. (2019). A Survey of Sentiment Analysis Based on Transfer Learning. IEEE Access, 7, 85401–85412.
Lynch, C., Aryafar, K., & Attenberg, J. (2015). Images Don’t Lie: Transferring Deep Visual Semantic Features to Large-Scale Multimodal Learning to Rank. ArXiv:1511.06746 [Cs].
Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. Proceedings of the 28th International Conference on International Conference on Machine Learning, 689–696.
Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Raghu, M., Zhang, C., Kleinberg, J., & Bengio, S. (2019). Transfusion: Understanding Transfer Learning for Medical Imaging. ArXiv:1902.07208 [Cs, Stat].
Reilly, W. J. (1929). Methods for the study of retail relationships. Austin, Tex.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why Should I Trust You?”: Explaining the
Predictions of Any Classifier. ArXiv:1602.04938 [Cs, Stat]. 45
Schonlau, M. (2005). Boosted Regression (Boosting): An Introductory Tutorial and a Stata Plugin. The Stata Journal, 5(3), 330–354.
Simonyan, K., & Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. ArXiv:1409.1556 [Cs].
Vargas, L. G. (1990). An overview of the analytic hierarchy process and its applications. European Journal of Operational Research, 48(1), 2–8.
Wright, M. N., & Ziegler, A. (2017). ranger: A Fast Implementation of Random Forests for High Dimensional Data in C++ and R. Journal of Statistical Software, 77(1).
Yang, Y., Tang, J., Luo, H., & Law, R. (2015). Hotel location evaluation: A combination of
machine learning tools and web GIS. International Journal of Hospitality
Management, 47, 14–24.
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in
deep neural networks? ArXiv:1411.1792 [Cs].
Zhang, W., Deng, L., Zhang, L., & Wu, D. (2021). A Survey on Negative Transfer.
ArXiv:2009.00909 [Cs, Stat].
Altmann, A., Toloşi, L., Sander, O., & Lengauer, T. (2010). Permutation importance: A
corrected feature importance measure. Bioinformatics, 26(10), 1340–1347. Heaton, J. (2018). Ian Goodfellow, Yoshua Bengio, and Aaron Courville: Deep learning.
Genetic Programming and Evolvable Machines, 19(1), 305–307.
Huff, D. L. (1964). Defining and Estimating a Trading Area. Journal of Marketing, 28(3),
34–38.
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F.,
Wattenberg, M., Corrado, G., Hughes, M., & Dean, J. (2017). Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. Transactions of the Association for Computational Linguistics, 5, 339–351.
Kuo, R. J., Chi, S. C., & Kao, S. S. (2002). A decision support system for selecting convenience store location through integration of fuzzy AHP and artificial neural network. Computers in Industry, 47, 199–214.
Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., & Ng, A. Y. (2011). Multimodal deep learning. Proceedings of the 28th International Conference on International Conference on Machine Learning, 689–696.
Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. ArXiv:1602.04938 [Cs, Stat].
Yang, Y., Tang, J., Luo, H., & Law, R. (2015). Hotel location evaluation: A combination of machine learning tools and web GIS. International Journal of Hospitality Management, 47, 14–24.
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? ArXiv:1411.1792 [Cs].
劉奕宏. (2011). 地理資訊系統及資料探勘技術在連鎖咖啡店設點之分析與研究. 政治 大學資訊科學系碩士學位論文
連財賢. (2016). 連鎖便利店選址作業模式之探討. 臺北科技大學工業工程與管理系 EMBA 碩士論文
呂珍珍. (2019). 連鎖咖啡品牌展店選址之研究-以高雄地區為例. 高雄大學創意設計 與建築學系碩士學位論文
杜逸寧, 徐維澤, 黃祥晉, 許明楷, 林鈺翔, & 洪健傑. (2018). 結合政府開放資料集於 建構開業選址決策支援系統--以店址當地消費能力與鄰近產業特性觀點. 215,
4–1.
商工行政資料開放平臺 -資料目錄-全國 4 大超商資料集. (2018). Retrieved from
https://data.gcis.nat.gov.tw/od/detail?oid=0202BFA9-8116-4E63-A41A- 58A5F4EAF7A2
地理資訊圖資雲服務平台.(2019). Retrieved from https://www.tgos.tw/tgos/Web/Address/TGOS_Address.aspx
高雄市公有路外停車場一覽表.(2019).高雄市政府資料開放.. Retrieved from https://data.kcg.gov.tw/dataset/department-of-transportation30
高雄市公車動態資訊.(2019). Retrieved from https://ibus.tbkc.gov.tw/bus/BusRoute.aspx
高雄捷運全球資訊網.(2019). Retrieved from https://www.krtc.com.tw/
電子全文 Fulltext
本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。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus:開放下載的時間 available 2026-09-15

您的 IP(校外) 位址是 44.222.134.250
現在時間是 2024-10-15
論文校外開放下載的時間是 2026-09-15

Your IP address is 44.222.134.250
The current date is 2024-10-15
This thesis will be available to you on 2026-09-15.

紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code