Deep CTR Prediction in Display Advertising
This addresses CTR prediction for image ads in online advertising systems, offering a novel method to improve accuracy over traditional logistic regression.
The paper tackled the problem of click-through rate (CTR) prediction in display advertising by introducing a deep neural network model that uses raw image pixels and contextual features, achieving effectiveness and efficiency on a real-world dataset with over 50 million records.
Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model. However, LR model lacks the ability of extracting complex and intrinsic nonlinear features from handcrafted high-dimensional image features, which limits its effectiveness. To solve this issue, in this paper, we introduce a novel deep neural network (DNN) based model that directly predicts the CTR of an image ad based on raw image pixels and other basic features in one step. The DNN model employs convolution layers to automatically extract representative visual features from images, and nonlinear CTR features are then learned from visual features and other contextual features by using fully-connected layers. Empirical evaluations on a real world dataset with over 50 million records demonstrate the effectiveness and efficiency of this method.