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.
