An Enhanced Ad Event-Prediction Method Based on Feature Engineering

摘要

In digital advertising, Click-Through Rate (CTR) and Conversion Rate (CVR) are veryimportant metrics for evaluating ad performance. As a result, ad event prediction systems arevital and widely used for sponsored search and display advertising as well as Real-TimeBidding (RTB). In this work, we introduce an enhanced method for ad event prediction (i.e.clicks, conversions) by proposing a new efficient feature engineering approach. A large realworldevent-based dataset of a running marketing campaign is used to evaluate the efficiency ofthe proposed prediction algorithm. The results illustrate the benefits of the proposed ad eventprediction approach, which significantly outperforms the alternative ones.