CaliCausalRank: Calibrated Multi-Objective Ad Ranking with Robust Counterfactual Utility Optimization
Not on the map. Why?
Abstract (arXiv)
Ad ranking systems must simultaneously optimize multiple objectives including click-through rate (CTR), conversion rate (CVR), revenue, and user experience metrics. However, production systems face critical challenges: score scale inconsistency across traffic segments undermines threshold transferability, and position bias in click logs causes offline-online metric discrepancies. We propose CaliCausalRank, a unified framework that integrates training-time scale calibration, constraint-based multi-objective optimization, and robust counterfactual utility estimation. Our approach treats score calibration as a first-class training objective rather than post-hoc processing, employs Lagrangian relaxation for constraint satisfaction, and utilizes variance-reduced counterfactual estimators for reliable offline evaluation. Experiments on the Criteo and Avazu datasets demonstrate that CaliCausalRank achieves 1.1% relative AUC improvement, 31.6% calibration error reduction, and 3.2% utility gain compared to the best baseline (PairRank) while maintaining consistent performance across different traffic segments.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 22 of its 36 references that are in the map. First posted on arXiv 21 Feb 2026.
Builds on
22 of 36 references.
References · 22
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2017DeepFM: A Factorization-Machine based Neural Network for CTR Predictioncited by 673
- 2017Deep Interest Network for Click-Through Rate Predictioncited by 541
- 2020DCN V2: Improved Deep & Cross Network and Practical Lessons for Web-scale Learning to Rank Systemscited by 326
- 2018Top-K Off-Policy Correction for a REINFORCE Recommender Systemcited by 181
- 2016Unbiased Learning-to-Rank with Biased Feedbackcited by 155
- 2018Unbiased Learning to Rank with Unbiased Propensity Estimationcited by 61
- 2022ESCM2: Entire Space Counterfactual Multi-Task Model for Post-Click Conversion Rate Estimationcited by 47
- 2021Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertisingcited by 39
- 2020Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactionscited by 35
- 2025Trustworthy Summarization via Uncertainty Quantification and Risk Awareness in Large Language Modelscited by 10
- 2025Dynamic Prompt Fusion for Multi-Task and Cross-Domain Adaptation in LLMscited by 9
10 more
- 2025Structural Generalization for Microservice Routing Using Graph Neural Networkscited by 6
- 2025Multi-Objective Adaptive Rate Limiting in Microservices Using Deep Reinforcement Learningcited by 5
- 2025Deep Learning Approach for Clinical Risk Identification Using Transformer Modeling of Heterogeneous EHR Datacited by 5
- 2025Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Modelscited by 5
- 2025Deep Q-Learning-Based Intelligent Scheduling for ETL Optimization in Heterogeneous Data Environmentscited by 4
- 2025LLM-Centric RAG with Multi-Granular Indexing and Confidence Constraintscited by 3
- 2025Structure-Aware Decoding Mechanisms for Complex Entity Extraction with Large-Scale Language Modelscited by 3
- 2025Spatiotemporal Traffic Prediction in Distributed Backend Systems via Graph Neural Networkscited by 2
- 2025Machine Learning Approaches to Clinical Risk Prediction: Multi-Scale Temporal Alignment in Electronic Health Recordscited by 2
- 2025Adaptive Human-Computer Interaction Strategies Through Reinforcement Learning in Complexcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.