Deep Learning for User Interest and Response Prediction in Online Display Advertising

Abstract

User interest and behavior modeling is a critical step in online digital advertising. On the one hand, user interests directly impact their response and actions to the displayed advertisement (Ad). On the other hand, user interests can further help determine the probability of an Ad viewer becoming a buying customer. To date, existing methods for Ad click prediction, or click-through rate prediction, mainly consider representing users as a static feature set and train machine learning classifiers to predict clicks. Such approaches do not consider temporal variance and changes in user behaviors, and solely rely on given features for learning. In this paper, we propose two deep learning-based frameworks, LSTM cp and LSTM ip , for user click prediction and user interest modeling. Our goal is to accurately predict (1) the probability of a user clicking on an Ad and (2) the probability of a user clicking a specific type of Ad campaign. To achieve the goal, we collect page information displayed to the users as a temporal sequence and use long short-term memory (LSTM) network to learn features that represents user interests as latent features. Experiments and comparisons on real-world data show that, compared to existing static set-based approaches, considering sequences and temporal variance of user requests results in improvements in user Ad response prediction and campaign specific user Ad click prediction.

Categorizing Natural Language-Based Customer Satisfaction: An Implementation Method Using Support Vector Machine and Long Short-Term Memory Neural Network

“…Similarly, LSTM has been used for wide range of text categorization applications, such as those applied in healthcare [22], settlement tweets [23], patents [24], hotel sentiment analysis [25], among others. LSTM has also been found to have better accuracy as compared to convolutional neural network (CNN), k-nearest neighbors (KNN), naïve bayes, among others [24], [26], [27], [28]. Specifically, in one study, LSTM was found to performed better in small sample size if the number of hidden units and word embedding dimensions are set at both 50 [29].…”

Prediction of instantaneous likeability of advertisements using deep learning

“…Long short-term memory (LSTM) [39], a special type of recurrent neural network (RNN), is also being practised by researchers to address different problems of sequences, especially for prediction of time series data. Gharibshah et al [40] proposed an LSTM-based framework to predict the probability of a user clicking on a website of advertisement either independently or in-campaign from the chronological sequence of historically visited websites. The architecture of CNN and LSTM are also combined together, in which the former is used for extraction of audiovisual features and the latter is for supporting sequence prediction [41,42].…”

Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks

“…Classifying user interests is one of the most important steps in personalized advertising as it provides information about users’ interests that could be used by marketers or advertisers. There have been various studies to classify users’ interests [ 25 , 26 , 27 , 28 , 29 ]. A study on SNS suggests a classification method to classify users’ active communication through comments into a grading system using Word2vec and support vector machine (SVM) classifier [ 25 ].…”

“…However, users’ comments are categorized using topic modeling and classification techniques to address the inconvenience that users face in reading numerous comments daily [ 27 ]. Another study uses deep learning to predict the probability of clicking an ad by associating it with user interests to predict the user’s interest and response to ads shown online [ 28 ]. In order to provide convenience to email users, e-mails are classified through the segmentation of intent in e-mail.…”