現今的社會之中，每天有有數百數千計的店鋪開業和歇業，決定店面的位置是相當重要的一件事。 對於零售店設立店鋪的選址條件，人潮流量為其中最為重要的評量指標之一。 由於在商業上得以節省成本以及獲得更大利潤，過去利用人潮流量評估最佳開設店鋪的問題在許多不同的領域中被廣為研究。 本研究以機器學習方法切入，將設立店鋪候補地點周遭環境特徵分佈圖像化，增加資料的可利用性與強化周遭環境特徵彼此之間的影響力，進而優化對於最佳地點選取的結果。 在本研究中，提出以四種影響人潮流量特徵為主的最佳地點預測模型，把圖像化後的特徵分佈，透過卷積神經網路處理，找出特徵之間的關聯性之後，就此關聯性作出最佳地點評估。 與過去研究相較之下，本研究之方法可以增加資料的使用率，對於評估規模較小或特徵較少的資料集也能有良好的表現。

In today's society, thousands of shops were opened and go out of business constantly every day. Determining the location of new branch store is a very important and critical issue for retail business. A store with high popularity will bring lots of profits for business owners. In the past, making decisions for locations of new stores has been widely studied in many fields considering cost saving and profits. . In this study, we use machine learning based methods to map the distribution of environmental features around the candidate locations of the store. Our proposed methods can make use of available open data and enhance the correlations between surrounding environmental features and popularity, and then thereby optimizing the results for the best location selection. In this study, the proposed methods are based on four kinds of human behaviors which can be easily extracted from location-based social network data. We treat them as imaged features and the imaged feature distributions are processed through the convolutional neural network to find the correlations between features and popularity. According to our experimental results, the proposed methods can increase usage of data, and can also perform well for datasets with less features comparing with past studies.

Key words: Popular Location Prediction, Convolutional Neural Network (CNN), Optimal Retail Store Location, Feature Engineering

References
[1] C.-C. Chang and C.-J. Lin, "LIBSVM: A library for support vector machines," ACM Trans. Intell. Syst. Technol., vol. 2, no. 3, pp. 1-27, 2011.
[2] W. Christaller and C. Baskin, Central Places in Southern Germany, The Pioneer Work in Theoretical Economic Geography (null). 1966, p. null.
[3] C. Cortes and V. Vapnik, "Support-vector networks," Machine Learning, journal article vol. 20, no. 3, pp. 273-297, September 01 1995.
[4] H. Damavandi, N. Abdolvand, and F. Karimipour, "The Computational Techniques for Optimal Store Placement: A Review," Cham, 2018, pp. 447-460: Springer International Publishing.
[5] H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support vector regression machines," presented at the Proceedings of the 9th International Conference on Neural Information Processing Systems, Denver, Colorado, 1996.
[6] P. Fischer, A. Dosovitskiy, and T. Brox, Image Orientation Estimation with Convolutional Networks. 2015, pp. 368-378.
[7] H. Hotelling, "Stability in Competition," (in English), Economic Journal, vol. 39, no. 153, pp. 41-57, Mar 1929. Wiley on behalf of the Royal Economic Society
[8] D. Karamshuk, A. Noulas, S. Scellato, V. Nicosia, and C. Mascolo, "Geo-spotting: mining online location-based services for optimal retail store placement," presented at the Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, Chicago, Illinois, USA, 2013.
[9] A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," presented at the Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 1, Lake Tahoe, Nevada, 2012.
[10] Y. Lecun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[11] J. Lian, F. Zhang, X. Xie, and G. Sun, "Restaurant Survival Analysis with Heterogeneous Information," presented at the Proceedings of the 26th International Conference on World Wide Web Companion, Perth, Australia, 2017.
[12] S. Mahendran, H. Ali, and R. Vidal, "3D Pose Regression Using Convolutional Neural Networks," in 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2017, pp. 494-495.
[13] T. Shimobaba, T. Kakue, and T. Ito, Convolutional Neural Network-Based Regression for Depth Prediction in Digital Holography. 2018, pp. 1323-1326.
[14] D. Yang, D. Zhang, and B. Qu, "Participatory Cultural Mapping Based on Collective Behavior Data in Location-Based Social Networks," ACM Trans. Intell. Syst. Technol., vol. 7, no. 3, pp. 1-23, 2016.
[15] Z. Yu, D. Zhang, and D. Yang, "Where is the Largest Market: Ranking Areas by Popularity from Location Based Social Networks," presented at the 2013 IEEE 10th International Conference on Ubiquitous Intelligence and Computing and 2013 IEEE 10th International Conference on Autonomic and Trusted Computing, Vietri sul Mere, 2013.
[16] Y. Zhang, B. Li, and J. Hong, "Understanding User Economic Behavior in the City Using Large-scale Geotagged and Crowdsourced Data," presented at the Proceedings of the 25th International Conference on World Wide Web, Montreal, Canada, 2016.