An accuracy improving method for advertising click through rate prediction based on enhanced xDeepFM model
This work addresses CTR prediction for enterprises to improve ad placement decisions, but it is incremental as it builds on existing xDeepFM architecture with specific enhancements.
The paper tackled the problem of advertising click-through rate (CTR) prediction by proposing an improved model based on xDeepFM, which integrates a multi-head attention mechanism and replaces the linear model with a Factorization Machine to better handle data sparsity and feature interactions. Experimental results on the Criteo dataset showed significant improvements in AUC and Logloss metrics compared to state-of-the-art methods.
Advertising click-through rate (CTR) prediction aims to forecast the probability that a user will click on an advertisement in a given context, thus providing enterprises with decision support for product ranking and ad placement. However, CTR prediction faces challenges such as data sparsity and class imbalance, which adversely affect model training effectiveness. Moreover, most current CTR prediction models fail to fully explore the associations among user history, interests, and target advertisements from multiple perspectives, neglecting important information at different levels. To address these issues, this paper proposes an improved CTR prediction model based on the xDeepFM architecture. By integrating a multi-head attention mechanism, the model can simultaneously focus on different aspects of feature interactions, enhancing its ability to learn intricate patterns without significantly increasing computational complexity. Furthermore, replacing the linear model with a Factorization Machine (FM) model improves the handling of high-dimensional sparse data by flexibly capturing both first-order and second-order feature interactions. Experimental results on the Criteo dataset demonstrate that the proposed model outperforms other state-of-the-art methods, showing significant improvements in both AUC and Logloss metrics. This enhancement facilitates better mining of implicit relationships between features and improves the accuracy of advertising CTR prediction.