CTR Prediction on Alibaba's Taobao Advertising Dataset Using Traditional and Deep Learning Models

TL;DR

Using a Taobao CTR dataset, the authors compare traditional static-feature approaches (LR, LightGBM) with neural and sequence-aware architectures, culminating in a Transformer-based model that leverages user behavior sequences. The Transformer achieves the strongest offline performance (AUC 0.6870), underscoring the value of temporal attention in modeling user engagement. An end-to-end A/B testing plan is proposed to validate real-world gains and inform deployment, with discussion of practical challenges and broader societal implications, including public health applications. The work provides a scalable roadmap for advanced CTR prediction and demonstrates how rich behavioral signals can enhance ad matching beyond e-commerce contexts.

Abstract

Click-through rates prediction is critical in modern advertising systems, where ranking relevance and user engagement directly impact platform efficiency and business value. In this project, we explore how to model CTR more effectively using a large-scale Taobao dataset released by Alibaba. We start with supervised learning models, including logistic regression and Light-GBM, that are trained on static features such as user demographics, ad attributes, and contextual metadata. These models provide fast, interpretable benchmarks, but have limited capabilities to capture patterns of behavior that drive clicks. To better model user intent, we combined behavioral data from hundreds of millions of interactions over a 22-day period. By extracting and encoding user action sequences, we construct representations of user interests over time. We use deep learning models to fuse behavioral embeddings with static features. Among them, multilayer perceptrons (MLPs) have achieved significant performance improvements. To capture temporal dynamics, we designed a Transformer-based architecture that uses a self-attention mechanism to learn contextual dependencies across behavioral sequences, modeling not only what the user interacts with, but also the timing and frequency of interactions. Transformer improves AUC by 2.81 % over the baseline (LR model), with the largest gains observed for users whose interests are diverse or change over time. In addition to modeling, we propose an A/B testing strategy for real-world evaluation. We also think about the broader implications: personalized ad targeting technology can be applied to public health scenarios to achieve precise delivery of health information or behavior guidance. Our research provides a roadmap for advancing click-through rate predictions and extending their value beyond e-commerce.

Figures (4)

• Figure 1: User behavior across city tiers
• Figure 2: Ad feature analysis: brand exposure, price gradient, and CTR distribution
• Figure 3: Consumption level and shopping depth by gender
• Figure 4: Temporal patterns in impressions, clicks, and CTR