Click-through Rate Prediction Research Articles

Deep Field Relation Neural Network for click-through rate prediction

Click-Through Rate (CTR) prediction is crucial in calculating advertisements and recommendation systems. To effectively predict CTR, it is important to properly model the interaction among features of data. This work tends to fully utilise the interaction information among features while employing deep neural networks for CTR prediction. To this end, we propose a Deep Field Relation Neural Network (DFRNN), which models feature interaction via a 3-dimensional relation tensor. The proposed method is evaluated on real data sets and compared with related methods. The results demonstrate that our method could be used to derive significant information contained in feature interaction and achieve an accurate CTR prediction.

Aspect-level sentiment capsule network for micro-video click-through rate prediction

Micro-videos, a new form of videos that are constrained in duration, gain significant popularity in recent years. The volume and rate of online micro-videos urgently calls for effective recommendation algorithms to help users find their interested ones. Although some previous works have investigated how to model users’ historical behaviors to predict the click-through rate of micro-videos, they are generally based on positive feedback only but overlook the negative which can help understand user preference at a finer granularity. The positive and negative feedback jointly imply the user’s different sentiments on different aspects, where each aspect is one component of a micro-video such as video_scene and video_subject. To this end, we propose an a spect-level s entiment cap sule network(ASCap) for micro-video click-through rate prediction by aggregating both positive and negative feedback, with an attempt to make the prediction more explainable. More specifically, an aspect-specific gating mechanism is firstly utilized to extract the aspect-level features from the target micro-video and the user’s positive and negative feedback. Then, in the following sentiment capsule network, the aspect-level features of the target micro-video are paired with those of positive and negative feedback respectively to identify their sentiments and form the sentiment capsules. Finally, the prediction layer is employed to calculate the overall click probability based on the sentiment capsules. Experimental results on two real-world micro-video datasets demonstrate that the proposed method significantly outperforms the state-of-the-art methods.

Position-Aware Deep Character-Level CTR Prediction for Sponsored Search

Predicting the click-through rate of an advertisement is a critical component of online advertising platforms. In sponsored search, the click-through rate estimates the probability that a displayed advertisement is clicked by a user after she submits a query to the search engine. Commercial search engines typically rely on machine learning models trained with a large number of features to make such predictions. This inevitably requires a lot of engineering efforts to define, compute, and select the appropriate features. In this paper, we propose two novel approaches (one working at character level and the other working at word level) that use deep convolutional neural networks to predict the click-through rate of a query-advertisement pair. Specifically, the proposed architectures consider as input only the textual content appearing in a query-advertisement pair and the page position at which the advertisement appears on the search result page of the query, and produce as output a click-through rate prediction. By comparing the character-level model with the word-level model, we show that language representation can be learnt from scratch at character level when trained on enough data. Through extensive experiments using billions of query-advertisement pairs of a popular commercial search engine, we demonstrate that both approaches significantly outperform a baseline model built on well-selected text features and a state-of-the-art word2vec-based approach. We also show the importance of the position feature in the proposed approaches in improving the prediction accuracy. When combining the predictions of the deep models introduced in this study with the prediction of the model in production of the same commercial search engine, we significantly improve the accuracy and the calibration of the click-through rate prediction of the production system. We also show the potential of leveraging the CTR prediction of the proposed deep learning models for query-ad relevance modeling and query-ad matching tasks in sponsored search.

A joint learning model for click-through prediction in display advertising

Click-through rate (CTR) prediction is essential for targeted advertising and recommendation. At present, machine learning models are widely used to build CTR estimators, including logistic regression (LR), factorization machine (FM), and deep neural network (DNN). Unfortunately, these models adopt the single structure that only considers either low-order feature interactions (such as LR and FM) or high-order feature interactions (such as DNN), not sufficient for CTR prediction. Therefore, the joint learning models are proposed, such as Wide & Deep and DeepFM, which can exploit both high- and low-order feature interactions to predict CTR by combining two different models. In this paper, we first analyze the typical CTR prediction models’ structures and performance, and then summarize the general form and design rules of CTR estimators. Based on the general form, we further design a new joint learning model that combines two different residual networks to explore the feature interactions automatically. Compared with the widely adopted feed-forward neural network, the residual network is more capable of exploring complex feature interactions at different layers. Additionally, we introduce a neural attention network to learn the importance of each second-order interaction of features from various fields. Finally, we evaluate the prediction performance of the proposed model based on two real-world datasets (i.e., Criteo and Avazu) in terms of LogLoss and AUC metrics. The extensive experimental results demonstrate our model performs the best compared to the state-of-the-art baselines.

Coarse-to-fine: A dual-view attention network for click-through rate prediction

Click-Through Rate (CTR) prediction is one of the most challenging tasks in the advertising systems, which aims to estimate the probability of a candidate user clicking on a candidate item. Recently, CTR prediction has observed remarkable progress, due to the advances of the Deep Neural network (DNN) in learning representation. However, most of the existing DNN-based methods focus on modeling implicit information from the user aspect, while ignoring the correlations between the user and other objects in the historical interactive behaviors (e.g., user→items or user→users). Additionally, the large-scale historical interactive behaviors also bring the model a lot of difficulty in finding precise relations from redundant and noisy data. Targeted at the above issues, our paper introduces a simple yet effective model, which boosts the user-view and item-view (i.e., dual-view) to extract various interactive relationships for CTR prediction. Therefore, we name our model as Dual-View Attention Network (DVAN). More specifically, we propose a cross-domain attention module (i.e., user→items and item→users) to extract the coarse-level correlations, and a local homogeneous-domain attention module (i.e., user→users and item→items) to extract the fine-level correlations adaptively. In order to extract the accurate relationship from the large-scale historical behaviors, a novel selection mechanism is introduced to connect the cross-domain attention module and the local homogeneous-domain attention module, and thus builds representation from the coarse-level to the fine-level gradually. Experimental results on four public datasets have demonstrated the effectiveness of our method, which outperforms existing state-of-the-art methods.

Core Interest Network for Click-Through Rate Prediction

In modern online advertising systems, the click-through rate (CTR) is an important index to measure the popularity of an item. It refers to the ratio of users who click on a specific advertisement to the number of total users who view it. Predicting the CTR of an item in advance can improve the accuracy of the advertisement recommendation. And it is commonly calculated based on users’ interests. Thus, extracting users’ interests is of great importance in CTR prediction tasks. In the literature, a lot of studies treat the interaction between users and items as sequential data and apply the recurrent neural network (RNN) model to extract users’ interests. However, these solutions cannot handle the case when the sequence length is relatively long, e.g., over 100. This is because of the vanishing gradient problem of RNN, i.e., the model cannot learn a users’ previous behaviors that are too far away from the current moment. To address this problem, we propose a new Core Interest Network (CIN) model to mitigate the problem of a long sequence in the CTR prediction task with sequential data. In brief, we first extract the core interests of users and then use the refined data as the input of subsequent learning tasks. Extensive evaluations on real dataset show that our CIN model can outperform the state-of-the-art solutions in terms of prediction accuracy.

Explicit Sparse Self-Attentive Network for CTR Prediction

Abstract The click-through rate (CTR) prediction is an essential task in the recommendation system. Available raw category features and feature combinations are important for CTR prediction, but their sparsity and high-dimension lead to huge computation. In recent years, methods based on deep learning, factorization machines and attention mechanism are widely used to model feature interactions among features for effective sparse predictive analysis. However, these previous algorithms are affected by irrelevant information. In this paper, we propose a novel model ESAtInt to model high-dimensional and sparse features, while being able to explicitly select meaningful higher-order feature interactions and eliminate the impact of irrelevant information. Specifically, we further conduct automatic feature interaction learning through a concentrated attention mechanism with explicit selection. Our model can explicitly select the most relevant parts to emphasize the attention to global features. Experimental results on the real-world dataset show that our proposed method is superior to state-of-the-art approaches for CTR prediction.

Deep User Segment Interest Network Modeling for Click-Through Rate Prediction of Online Advertising

Online advertising is becoming an important direction in the advertising industry with its strengths in diverse users, strong interactions, real-time feedback, and expandability. Online advertisement (Ads) can show great marketing ability by processing data from multiple channels to convey information, understanding what users want, and approaching them easily. Moreover, predicting the click-through rate (CTR) can increase advertisement revenue and user satisfaction. However, advertising data contains many features, and the amount is growing rapidly. This can be alleviated through the segmentation of users with similar interests. We assumed that the change of interest of a user could be predicted by other users’ change of interest. More specifically, similar users will change their interest in a similar direction. On the basis of this idea, we proposed a novel model, the Deep User Segment Interest Network, to improve CTR prediction. We suggested three novel layers for improving performance: i) an individual interest extractor, ii) a segment interest extractor, and iii) a segment interest activation. These layers captures the latent interest of each user and creates the expressive interest representation of the segment by aggregating each user’s interest. We conducted experiments using TaoBao data, which are a kind of real commercial data from an advertising platform, to confirm the CTR prediction improvement by reflecting the segment interest. The proposed algorithm obtained an AUC gain of 0.0029 with a behavior sequence length of 100. This performance exhibited the greatest improvement over other baselines, indicating the proposed method’s potential contribution to business improvement.

Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction.

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction.

Advertising Click-Through Rate Prediction Based on CNN-LSTM Neural Network.

In the era of big data information, how to effectively predict and analyze the click-through rate of information advertising is the key for enterprises in various fields to seek returns. The point rate prediction of advertising is one of the core contents of advertising calculation. The traditional shallow prediction model cannot meet the nonlinear relationship of data processing, and the manual processing of data information extraction method is very resource consuming. To solve the above problems, this paper proposes a CNN-LSTM (convolutional neural network-long short-term memory) convolution hybrid neural network algorithm to predict the click-through rate of advertisements. According to the neural network algorithm, the prediction model is constructed, and the effective features are extracted in the process of model establishment, and the prediction analysis is carried out according to the simplified LSTM neural network time serialization features. CNN convolution neural network is used to train the prediction model. This paper analyzes the characteristics of traditional prediction methods and the corresponding solutions and carries out feature learning and prediction model construction for advertising click-through rate prediction. Then, the unknown behavior of advertising users is judged and predicted. The results show that, compared with the single structure network of traditional prediction model, the prediction effect based on CNN-LSTM neural network algorithm has higher accuracy.

Learning Dynamic User Interest Sequence in Knowledge Graphs for Click-Through Rate Prediction

Despite that path-based and embedding-based models with knowledge graphs (KGs) achieve better recommendation performance compared with other deep learning based methods, such improvement is limited due to a lack of modeling user's dynamic interest. To address this issue, we explore a principled model to provide semantic understanding of each item in user's historical interest sequence in KGs. Specifically, we propose a multi-granularity dynamic interest sequence learning method, which is based on knowledge-enhanced path mining and interest fluctuation signal discovery, to obtain semantic-enhanced paths. Furthermore, the paths are embedded by the SEP2Vec, and merged through the proposed entropy-aware pooling layer to obtain the user preference representation, which is then used to learn dynamic user interest sequence. Experimental results on two public datasets of movie and music recommendation, and two industrial datasets of personalized local service recommendation in Alipay App have illustrated that the proposed model can achieve significantly better prediction performance compared with other known baselines.

GCN-Int: A Click-Through Rate Prediction Model Based on Graph Convolutional Network Interaction

Recommendation system has drawn growing attention in the academia and industry because it can solve the problem of information overload. Among a variety of methods, the click-through rate prediction model plays an important role in predicting user’s attention to a specific item. To predict click-through rate, high-dimensional and sparse features are usually adopted, and the accuracy of the prediction result depends on the combination of high-order features to a great extent. Therefore, many methods have been proposed to find the low-dimensional representation from sparse high-dimensional original features, and the meaningful way of feature combination has also been mined to improve the accuracy of the model. However, the click-through rate prediction models generally have two problems. One is that they can’t extract the feature interaction of non-Euclidean features very well. Another one is that it is hard to explain the inward meaning of feature interaction. In this paper, a GCN-int model based on the interaction of Graph Convolutional Network is proposed to solve the above problems. The proposed model simplifies the complex interaction among multiple features, gets a better representation of the interaction between high-order features, and improves the interpretability of feature interaction. The experimental results on the public movie recommendation dataset and our own IPTV movie recommendation dataset show that the proposed GCN-int model gets higher accuracy and efficiency compared with the state-of-the-art models.

Visualization Analysis on CNN Based CTR Prediction

클릭률(click through rate, CTR) 예측은 사용자에게 노출된 광고가 클릭될 확률을 추정하는 것으로 온라인 광고 수익 극대화를 위한 광고 노출 전략 결정에 중요한 역할을 담당한다. CTR 예측의 핵심은 데이터 필드(특징) 간 상호작용을 효과적으로 모델링하는 것인데 최근 시·공간적 연계성을 갖는 데이터에 있어 탁월한 성능을 발휘하고 있는 심층신경망(deep neural network)을 모델링에 활용한 연구가 활발히 진행되고 있다. 본 연구는 CTR 예측을 위해 이미지·음성 인식 분야에서 뛰어난 성능을 보여주고 있는 신경망 구조인 Convolutional Neural Network(CNN)의 활용가능성에 관한 기초적인 연구 결과를 제시한다. 먼저 이미지·음성 데이터와 구별되는 CTR 데이터의 특성과 이로 인한 CNN 적용 시 발생할 수 있는 성능상의 한계점을 도출한다. CNN의 하이퍼 파라미터인 임베딩과 풀링에 관한 비교 설정 실험 결과를 시각적으로 해석하여 CTR 데이터에 대한 하이퍼 파라미터의 영향력을 분석한다. 실험 결과에 따르면, CTR 데이터에 있어 임베딩과 풀링은 유기적으로 성능에 영향을 미치므로 데이터 특성에 맞게 둘 간의 최적 조합을 선택하는 것이 CNN 성능 향상에 매우 중요한 요소가 됨을 확인하였다.The click through rate(CTR) prediction estimates the probability that an advertisement exposed to a user is clicked, and plays an important role in determining an advertisement exposure strategy for maximizing online advertisement revenue. The key to predicting CTR is to effectively model the interactions between data fields(features). Recently, researches using deep neural network(DNN), which exhibits excellent performance in data with temporal and spatial correlation, are actively conducted for modeling. This study presents basic research results on the possibility of using a convolutional neural network(CNN), a neural network structure that shows the best performance in the image and speech recognition field, for CTR prediction. First, we derive the characteristics of CTR data that are distinguished from image and voice data and the performance limitations that can occur when regular CNN is applied. Then, we visually analyze the experiment results of the comparison setup for CNN hyperparameters(embedding and pooling) to understand the imapct of hyperparameters on CTR data. According to the experimental results, since embedding and pooling organically affect the performance of CTR data, it was confirmed that selecting the optimal combination between the two based on the data characteristics is a very important factor in improving CNN performance.

A New Click-Through Rates Prediction Model Based on Deep&Cross Network

With the development of E-commerce, online advertising began to thrive and has gradually developed into a new mode of business, of which Click-Through Rates (CTR) prediction is the essential driving technology. Given a user, commodities and scenarios, the CTR model can predict the user’s click probability of an online advertisement. Recently, great progress has been made with the introduction of Deep Neural Networks (DNN) into CTR. In order to further advance the DNN-based CTR prediction models, this paper introduces a new model of FO-FTRL-DCN, based on the prestigious model of Deep&Cross Network (DCN) augmented with the latest optimization technique of Follow The Regularized Leader (FTRL) for DNN. The extensive comparative experiments on the iPinYou datasets show that the proposed model has outperformed other state-of-the-art baselines, with better generalization across different datasets in the benchmark.

Modeling low- and high-order feature interactions with FM and self-attention network

Click-Through Rate (CTR) prediction has always been a very popular topic. In many online applications, such as online advertising and product recommendation, a small increase in CTR will bring great returns. However, CTR prediction has always faced several challenges. A large number of users and items and the different sizes of the feature space of different data types lead to high-dimensional and sparse input, and high-order feature interactions rely too much on expert knowledge and are very time-consuming. In this paper, we build a novel model called multi-order interactive features aware factorization machine (MoFM) for CTR prediction. To effectively capturing both low-order and high-order interactive features, three different types of prediction models are integrated, of which logistic regression (LR) and factorization machine (FM) model the original features and 2-order interactive features respectively, and a multi-head self-attention network with residual connections is used to automatically identify high-value high-order feature combinations. There is also an embedding layer in the model to realize a unified embedding processing of different data types, avoiding diversification, sparsity, and high dimensionality of features. Since, feature engineering is not required, we can carry out end-to-end model learning. Experiments on three public datasets show the superiority of the proposed model over the state-of-the-art models, and the flexibility and scalability of the model structure have also been verified.

Deep Dynamic Interest Learning With Session Local and Global Consistency for Click-Through Rate Predictions

Click-through rate (CTR) prediction is the core task in an online advertising system. How to capture the users’ dynamic interests through the behavior sequences to predict CTR is a challenging problem in the real-world applications. To address this challenge, we propose a deep dynamic interest learning by learning the local sessions and global sessions within sequences for CTR prediction. The local sessions and global sessions are used to capture the short-term dynamic interests and the long-term interests of users, respectively. To explore the heterogeneous behaviors within the global session efficiently, the interests in global sessions are forced to be consistent with that in local sessions. Then, the bi-LSTM network is adopted to capture the dynamic interests with the behaviors across global sessions effectively. Experimental results on various datasets show that the proposed method outperforms several state-of-the-art CTR prediction methods.

Attentive capsule network for click-through rate and conversion rate prediction in online advertising

Estimating Click-through Rate (CTR) and Conversion Rate (CVR) are two essential user response prediction tasks in computing advertising and recommendation systems. The mainstream methods map sparse, high-dimensional categorical features (e.g., user id, item id) into low-dimensional representations with neural networks. Although they have achieved significant advancement in recent years, how to capture user’s diverse interests effectively from past behaviors is still challenging. Recently some works try using attention-based methods to learn the representation from user behavior history adaptively. However, it is insufficient to capture the diversity of user’s interests. As a step forward to improve this goal, we propose a method named Attentive Capsule Network (ACN). It uses Transformers for feature interaction and leverages capsule networks to capture multiple interests from user behavior history. To precisely obtain sequence representation related to the current advertisement, we further design a modified dynamic routing algorithm integrating with an attention mechanism. Experimental results on real-world datasets demonstrate the effectiveness of our proposed ACN with significant improvement over state-of-the-art approaches. Moreover, it also offers good explainability when extracting diverse interest points of users from behavior history.

Multi-view feature transfer for click-through rate prediction

Click-through rate prediction is an important method for online advertising and marketing evaluations. However, for environmental reasons, there is a scarcity and imbalance in the advertising data available. We found that a feature transfer can be applied in a transfer learning method to obtain potential connections from less relevant advertisement data. Considering the complexity and diverse features of advertisement data, a feature transfer cannot allow researchers to discover the relationships among such features within the advertisement data. Therefore, we propose a click-through rate method based on a multi-view feature transfer (MFT). MFT divides the data into common and selected features during the data pretreatment process. It then combines the important feature vectors obtained using a Laplacian matrix with the common features obtained during the pretreatment process to form groups of views. Therefore, combining feature transfer matrix with mutli-view clustering is an innovation of the CTR data prediction process. In our experiments, the MFT model achieved good results. Experiments on a large number of datasets of different sizes and the application of three evaluation indicators show that the MFT method delivers excellent prediction results using the transfer relationships among the characteristics of an advertising dataset, and its performance is better than that of many other advertising click-through rate prediction methods.

An Attention-Based Latent Information Extraction Network (ALIEN) for High-Order Feature Interactions

One of the primary tasks for commercial recommender systems is to predict the probabilities of users clicking items, e.g., advertisements, music and products. This is because such predictions have a decisive impact on profitability. The classic recommendation algorithm, collaborative filtering (CF), still plays a vital role in many industrial recommender systems. However, although straight CF is good at capturing similar users’ preferences for items based on their past interactions, it lacks regarding (1) modeling the influences of users’ sequential patterns from their individual history interaction sequences and (2) the relevance of users’ and items’ attributes. In this work, we developed an attention-based latent information extraction network (ALIEN) for click-through rate prediction, to integrate (1) implicit user similarity in terms of click patterns (analogous to CF), and (2) modeling the low and high-order feature interactions and (3) historical sequence information. The new model is based on the deep learning, which goes beyond the capabilities of econometric approaches, such as matrix factorization (MF) and k-means. In addition, the approach provides explainability to the recommendation by interpreting the contributions of different features and historical interactions. We have conducted experiments on real-world datasets that demonstrate considerable improvements over strong baselines.

Neighborhood Aggregation Collaborative Filtering Based on Knowledge Graph

In recent years, the research of combining a knowledge graph with recommendation systems has caused widespread concern. By studying the interconnections in knowledge graphs, potential connections between users and items can be discovered, which provides abundant and complementary information for recommendation of items. However, most existing studies have not effectively established the relation between entities and users. Therefore, the recommendation results may be affected by some unrelated entities. In this paper, we propose a neighborhood aggregation collaborative filtering (NACF) based on knowledge graph. It uses the knowledge graph to spread and extract the user’s potential interest, and iteratively injects them into the user features with attentional deviation. We conducted a large number of experiments on three public datasets; we verifyied that NACF is ahead of the most advanced models in top-k recommendation and click-through rate (CTR) prediction.