Feature Enhancement via User Similarities Networks for Improved Click Prediction in Yahoo Gemini Native
| Autor: | Eliran Abutbul, Morelle Arian, Rotem Stram, Yair Koren, Oren Somekh, Michal Aharon |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Information retrieval
Computer science business.industry 02 engineering and technology Online advertising 020204 information systems 0202 electrical engineering electronic engineering information engineering Bipartite graph Collaborative filtering Revenue 020201 artificial intelligence & image processing The Internet Native advertising business |
| Zdroj: | CIKM |
| Popis: | Yahoo's native advertising marketplace (also known as Gemini native) serves billions of ad impressions daily, reaching many hundreds of millions USD in yearly revenue. Driving Gemini native models that are used to predict ad click probability (pCTR) is OFFSET - a feature enhanced collaborative-filtering (CF) based event prediction algorithm. While some of the user features used by OFFSET have high coverage, other features, especially those based on click patterns, suffer from extremely low coverage. In this work, we present a framework that simplifies complex interactions between users and other entities in a bipartite graph. The one mode projection of this bipartite graph onto users represents a user similarity network, allowing us to quantify similarities between users. This network is combined with existing user features to create an enhanced feature set. In particular, we describe the implementation and performance of our framework using user Internet browsing data (e.g., visited pages URLs) to enhance the user category feature. Using our framework we effectively increase the feature coverage by roughly 15%. Moreover, online results evaluated on 1% of Gemini native traffic show that using the enhanced feature increases revenue by almost 1% when compared to the baseline operating with the original feature, which is a substantial increase at scale. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|