Efficient Click-Through Rate Prediction for Developing Countries via Tabular Learning
This addresses the challenge of efficient online advertising deployment in resource-constrained environments, offering a practical solution with demonstrated performance gains.
The paper tackles the problem of deploying Click-Through Rate (CTR) prediction models in developing countries with limited computing resources by showing that tabular learning models are more efficient and effective than over-parameterized models, outperforming twelve state-of-the-art models on eight datasets and improving real user CTR in an A/B test.
Despite the rapid growth of online advertisement in developing countries, existing highly over-parameterized Click-Through Rate (CTR) prediction models are difficult to be deployed due to the limited computing resources. In this paper, by bridging the relationship between CTR prediction task and tabular learning, we present that tabular learning models are more efficient and effective in CTR prediction than over-parameterized CTR prediction models. Extensive experiments on eight public CTR prediction datasets show that tabular learning models outperform twelve state-of-the-art CTR prediction models. Furthermore, compared to over-parameterized CTR prediction models, tabular learning models can be fast trained without expensive computing resources including high-performance GPUs. Finally, through an A/B test on an actual online application, we show that tabular learning models improve not only offline performance but also the CTR of real users.