cs.AINov 17, 2026

COTTI: Contrastive Training and Time-Aware Inference for Robust Industrial Recommendation under Promotional Drift

Authors: Maolei Huang, Jing Tian, Dexuan Duan, Fangfang Lin, Huawei Cao, Shuhan Song

Organizations: Alibaba Group, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Santa Clara University, USA

Abstract

Promotional events shift traffic composition, purchase behavior, and the scale of conversion probabilities on different time horizons. We present COTTI (COntrastive Training and Time-aware Inference), an industrial recommendation framework that separates historical representation learning from event-time score adjustment. Cross-Period Contrastive Alignment (CPC) regularizes paired histories of the same user with adaptive consistency weights. Active Re-weighting (RW) controls the influence of promotional examples through historical-interest distance. Adaptive Boundary Alignment (ABA) combines stochastic prediction variability with a temporal event kernel to adjust logits while keeping predictor parameters fixed. We analyze the weighted objective and bound ABA-induced probability and ranking changes. On Fliggy data, COTTI attains an offline AUC of 0.8127, compared with 0.8101 for TEN and 0.8123 for TEN with ABA. Cross-category analysis reveals improved discrimination alongside declines in paid-item recall for novel categories. End-to-end measurements give a p99 latency of 38.9,ms and throughput of 14,700 requests/s; enabling ABA adds 2.2,ms to p99. A ten-day online experiment against the serving HDR model yields relative gains of 3.14% in conversion rate and 2.68% in revenue per mille. Together, these results characterize the trade-off between aggregate prediction, novel-category discovery, and serving cost in promotional recommendation.

Figures & tables

Explore similar work

CardsList
  1. CRM: Retrieval Model with Controllable Condition

    Dec 18, 2024Chi Liu, Jiangxia Cao, Rui Huang +5Recommender SystemsSequential Recommendation

  2. TokenFormer V2: Breaking the Resolution-Complexity Dilemma in Unified Recommendation

    Nov 14, 2026Kaihui Wu, Guoming Li, Liang Guo +8Recommender SystemsFeature Interaction Modeling