點擊率的預測在許多內容導向為主的資訊服務中一直有著非常重要的應用，這類服務如電子商務網站、影音串流平台與社群媒體網站，都會盡可能的將使用者會點擊的內容展示在最顯眼的位子，目的即是為了增加使用者使用服務的時間，使用者使用服務的時間增加自然能夠提升服務帶來的商業效益。
要如何找出使用者感興趣並且會點擊的內容一直以來都是推薦系統領域的研究重點，隨著近年來深度學習的興起與成功，已有許多國際大型公司將自身所提供的內容服務改以基於深度學習架構的推薦系統進行推薦，並且提出自行研發的深度學習模型。
我們發現這些成功應用深度學習的服務往往都有著國際級的超大型規模，相對的區域性中小型規模的服務就鮮少有看到成功使用深度學習的案例，這讓我們不禁懷疑時下流行的深度學習模型用於中小型服務的可行性，於是我們開始使用不同的深層與簡易模型對不同規模的資料進行實驗，我們發現深層模型的確不全然適用於中小規模的服務，但其與簡易模型一樣，有著一種在特定條件下逐漸準確的趨勢，也就是說不同的模型有著各自準確的時機，發現這點後，我們開始於不同時機選擇不同模型進行預測，最終提升了點擊率預測任務整體的準確性。

Click-through rate prediction has been an essential application in many content-oriented information services, such as e-commerce, video streaming platforms, and social media. These services display contents that users are likely to click in a prominent position. As a result, users may be attracted and spend more time on these services.
With the rise and success of deep learning in recent years, many large international companies have integrated their content services with recommendation systems based on the deep learning framework and proposed their deep learning models. However, it seems only the Internet giants reported successful stories on deep learning-based recommender systems. Consequently, we are suspicious of the feasibility of the deep learning models on small and medium-sized services, so we started experimenting with machine learning models with different complexity and datasets of different sizes. We found that deep learning models and simple models seem to appropriate in different cases. After discovering this, we proposed a model to select a recommendation algorithm based on the given scenario automatically. This selecting model improved the overall accuracy of the click-through rate prediction task.

[1] Rafael Alencar. 2017. Resampling strategies for imbalanced datasets. Kaggle. (2017). https://www.kaggle.com/rafjaa/resampling-strategies-for-imbalanceddatasets

[2] Alibaba. 2018. X-deeplearning. Github. (2018). https://github.com/alibaba/xdeeplearning

[3] Naomi S Altman. 1992. An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46, 3, 175–185. doi: 10.2307/2685209

[4] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. (2014). arXiv: 1409.0473 [cs.CL]

[5] Oren Barkan and Noam Koenigstein. 2016. Item2vec: neural item embedding for collaborative filtering. 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), (September 2016). doi: 10.1109/mlsp.2016.7738886

[6] Tianqi Chen and Carlos Guestrin. 2016. Xgboost: a scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). Association for Computing Machinery, San Francisco, California, USA, 785–794. isbn: 9781450342322. doi: 10.1145/2939672.2939785

[7] Heng-Tze Cheng, Levent Koc, Jeremiah Harmsen, Tal Shaked, Tushar Chandra, Hrishi Aradhye, Glen Anderson, Greg Corrado, Wei Chai, Mustafa Ispir, Rohan Anil, Zakaria Haque, Lichan Hong, Vihan Jain, Xiaobing Liu, and Hemal Shah. 2016. Wide & deep learning for recommender systems. In Proceedings of the 1st Workshop on Deep Learning for Recommender Systems (DLRS 2016). Association for Computing Machinery, Boston, MA, USA, 7–10. isbn: 9781450347952. doi: 10.1145/2988450.2988454

[8] François Chollet et al. 2015. Keras. (2015). https://keras.io

[9] Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16). Association for Computing Machinery, Boston, Massachusetts, USA, 191–198. isbn: 9781450340359. doi: 10.1145/2959100.2959190

[10] Yufei Feng, Fuyu Lv, Weichen Shen, Menghan Wang, Fei Sun, Yu Zhu, and Keping Yang. 2019. Deep session interest network for click-through rate prediction. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, (August 2019). doi: 10.24963/ijcai.2019/319

[11] David Goldberg, David Nichols, Brian M. Oki, and Douglas Terry. 1992. Using collaborative filtering to weave an information tapestry. Commun. ACM, 35, 12, (December 1992), 61–70. issn: 0001-0782. doi: 10.1145/138859.138867

[12] Mihajlo Grbovic and Haibin Cheng. 2018. Real-time personalization using embeddings for search ranking at airbnb. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18). Association for Computing Machinery, London, United Kingdom, 311–320. isbn: 9781450355520. doi: 10.1145/3219819.3219885

[13] Long Guo, Lifeng Hua, Rongfei Jia, Binqiang Zhao, Xiaobo Wang, and Bin Cui. 2019. Buying or browsing?: predicting real-time purchasing intent using attentionbased deep network with multiple behavior. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’19). Association for Computing Machinery, Anchorage, AK, USA, 1984–1992. isbn: 9781450362016. doi: 10.1145/3292500.3330670

[14] F. Maxwell Harper and Joseph A. Konstan. 2015. The movielens datasets: history and context. ACM Trans. Interact. Intell. Syst., 5, 4, Article 19, (December 2015), 19 pages. issn: 2160-6455. doi: 10.1145/2827872

[15] Jeff Johnson, Matthijs Douze, and Herve Jegou. 2019. Billion-scale similarity search with gpus. IEEE Transactions on Big Data. issn: 2372-2096. doi: 10.1109/tbdata.2019.2921572

[16] Guillaume Lemaître, Fernando Nogueira, and Christos K. Aridas. 2017. Imbalancedlearn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. Journal of Machine Learning Research, 18, 17, 1–5. issn: 1532-4435. http://jmlr.org/papers/v18/16-365.html

[17] G. Linden, B. Smith, and J. York. 2003. Amazon.com recommendations: item-toitem collaborative filtering. IEEE Internet Computing, 7, 1, 76–80. doi: 10.1109/MIC.2003.1167344

[18] Jiaqi Ma, Zhe Zhao, Xinyang Yi, Jilin Chen, Lichan Hong, and Ed H. Chi. 2018. Modeling task relationships in multi-task learning with multi-gate mixture-of-experts. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18). Association for Computing Machinery, London, United Kingdom, 1930–1939. isbn: 9781450355520. doi: 10.1145/3219819.3220007

[19] Martı́n Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S. Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Ian Goodfellow, Andrew Harp, Geoffrey Irving, Michael Isard, Yangqing Jia, Rafal Jozefowicz, Lukasz Kaiser, Manjunath Kudlur, Josh Levenberg, Dandelion Mané, Rajat Monga, Sherry Moore, Derek Murray, Chris Olah, Mike Schuster, Jonathon Shlens, Benoit Steiner, Ilya Sutskever, Kunal Talwar, Paul Tucker, Vincent Vanhoucke, Vijay Vasudevan, Fernanda Viégas, Oriol Vinyals, Pete Warden, Martin Wattenberg, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2015. TensorFlow: large-scale machine learning on heterogeneous systems. (2015). https://www.tensorflow.org/

[20] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. (2013). arXiv: 1301.3781 [cs.CL]

[21] Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Distributed representations of words and phrases and their compositionality. In Proceedings of the 26th International Conference on Neural Information Processing Systems - Volume 2 (NIPS’13). Curran Associates Inc., Lake Tahoe, Nevada, 3111–3119.

[22] Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, Jake Vanderplas, Alexandre Passos, David Cournapeau, Matthieu Brucher, Matthieu Perrot, and Édouard Duchesnay. 2011. Scikit-learn: machine learning in python. Journal of Machine Learning Research, 12, 85, 2825–2830. issn: 1532-4435. http://jmlr.org/papers/v12/pedregosa11a.html

[23] Radim Řehůřek and Petr Sojka. 2010. Software framework for topic modelling with large corpora. In Proceedings of LREC 2010 workshop New Challenges for NLP Frameworks. University of Malta, Valletta, Malta, 46–50. isbn: 2-9517408-6-7

[24] Xin Rong. 2014. Word2vec parameter learning explained. (2014). arXiv: 1411.2738 [cs.CL]

[25] Ying Shan, T. Ryan Hoens, Jian Jiao, Haijing Wang, Dong Yu, and JC Mao. 2016. Deep crossing: web-scale modeling without manually crafted combinatorial features. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD ’16). Association for Computing Machinery, San Francisco, California, USA, 255–262. isbn: 9781450342322. doi: 10.1145/2939672.2939704

[26] M. Slaney and M. Casey. 2008. Locality-sensitive hashing for finding nearest neighbors [lecture notes]. IEEE Signal Processing Magazine, 25, 2, 128–131. doi: 10.1109/MSP.2007.914237

[27] 2006. Introduction to data mining. (1st edition). Addison-Wesley. Chapter 8, 500. isbn: 0321321367

[28] TIANCHI. 2018. User behavior data from taobao for recommendation. Website. (May 2018). https://tianchi.aliyun.com/dataset/dataDetail?dataId=649

[29] I. Tomek. 1976. Two modifications of cnn. IEEE Transactions on Systems, Man, and Cybernetics, SMC-6, 11, 769–772. doi: 10.1109/TSMC.1976.4309452

[30] Weinan Zhang, Tianming Du, and Jun Wang. 2016. Deep learning over multi-field categorical data. Advances in Information Retrieval, 45–57. issn: 1611-3349. doi: 10.1007/978-3-319-30671-1_4

[31] Zhe Zhao, Lichan Hong, Li Wei, Jilin Chen, Aniruddh Nath, Shawn Andrews, Aditee Kumthekar, Maheswaran Sathiamoorthy, Xinyang Yi, and Ed Chi. 2019. Recommending what video to watch next: a multitask ranking system. In Proceedings of the 13th ACM Conference on Recommender Systems (RecSys ’19). Association for Computing Machinery, Copenhagen, Denmark, 43–51. isbn: 9781450362436. doi: 10.1145/3298689.3346997

[32] Guorui Zhou, Na Mou, Ying Fan, Qi Pi, Weijie Bian, Chang Zhou, Xiaoqiang Zhu, and Kun Gai. 2019. Deep interest evolution network for click-through rate prediction. Proceedings of the AAAI Conference on Artificial Intelligence, 33, (July 2019), 5941–5948. issn: 2159-5399. doi: 10.1609/aaai.v33i01.33015941

[33] Guorui Zhou, Xiaoqiang Zhu, Chenru Song, Ying Fan, Han Zhu, Xiao Ma, Yanghui Yan, Junqi Jin, Han Li, and Kun Gai. 2018. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD ’18). Association for Computing Machinery, London, United Kingdom, 1059–1068. isbn: 9781450355520. doi: 10.1145/3219819.3219823