Embedding fusion

Tencent Cloud Developer

Sep 3, 2020 · Artificial Intelligence

CTR Prediction Optimization for App Store Recommendation: Integrating DeepWalk, BERT, and Attention Mechanisms

The paper presents an optimized CTR prediction model for Tencent’s App Store that merges multi‑behavior shared embeddings, long‑term DeepWalk graph embeddings, BERT‑derived app description vectors, and attention‑based fusion, reducing parameters while improving bias, AUC, and recommendation performance for sparse, long‑tail data.