Skip to main content
Search

# Click-Through Rate Prediction

2 related articles

Subscribe to updates
  1. arXiv

    History compression stops being recomputed per candidate: X-split ARGUS lifts conversion value 4.65% in a live bidding system

    Click-through rate prediction needs long behavioral histories, yet re-encoding that history on every ranking request strains production compute and latency budgets. X-split ARGUS compresses history into a set of tokens that do not depend on the candidate, computes them offline and reuses them across requests, while the online ranker cross-attends to those tokens and to recent events for each candidate. Offline normalized entropy falls 0.81% relative to Context-aware ARGUS, retaining more than 70% of the uncompressed teacher's improvement; in an online A/B test conversion value rises 4.65% and clicks 2.96%, at the cost of 15% more online GPUs of the same type for the same traffic.

  2. arXiv

    LLaMA3-8B cut to 4.5B parameters: SlimFM moves LLM semantics into online CTR serving at about 16 ms

    Adding large-language-model semantics to click-through-rate prediction previously meant caching LLM outputs offline and serving only a small CTR model online. SlimFM prunes LLaMA3-8B to a 4.5B-parameter backbone with dependency-aware structured pruning, fine-tunes it with LoRA for field-level semantic embeddings, and injects those embeddings into a conventional CTR model's feature interactions. Across four datasets and six CTR backbones it retains over 99% of the uncompressed model's accuracy, with single-sample inference latency of 15.98–17.58 ms.

You’re all caught up