MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction

• URL: http://arxiv.org/abs/2608.10562v1
• Date: Tue, 11 Aug 2026 06:49:59 GMT
• Title: MARCO: Click-Intent Decomposition for Calibrated Ads Conversion Prediction
• Abstract summary: Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR)<n>Different click types on the same ad exhibit a 4-fold difference in actual conversion rates.<n>By conflating these signals, the standard CVR model under-predicts high-intent clicks and over-predicts low-intent ones.<n>We propose MARCO, a framework that resolves this bias by decomposing each click by intent.
• Score: 31.422771243113758
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Not all clicks are equal. Industrial ads ranking decouples conversion probability into click-through rate (CTR) and post-click conversion rate (CVR), yet treats every click as the same event. In reality, users provide a free, self-generated signal of intent through their physical UI interactions. Different click types on the same ad exhibit a 4-fold difference in actual conversion rates. By conflating these signals, the standard CVR model under-predicts high-intent clicks and over-predicts low-intent ones, which is a bias masked by near-perfect aggregate calibration. We propose MARCO (Multi-intent Ads Ranking Composition Optimization), a framework that resolves this bias by decomposing each click by intent. Using the logged click type as a free behavioral label, MARCO trains per-intent CVR heads on homogeneous populations, and at serving time composes their per-intent CVR estimates under a predicted distribution over intents. Theoretically, we prove that decomposition never raises population risk, give the exact headroom under squared loss and non-negativity under the deployed loss, and show through a routing-efficiency dial how much of it reaches serving. Because the population-optimal score is unchanged, any gain is a finite-capacity estimation and calibration effect that we validated both offline and online. For deployment at scale, we further cast multi-impression, multi-click attribution as credit assignment with a bias-variance tradeoff analogous to RL return estimation, showing last-impression, first-click attribution is the low-bias, low-variance, deterministic choice under production constraints, and derive three consistency conditions enforced end-to-end at scale. Deployed at binary intent granularity, MARCO corrects per-intent calibration to approximately 100%, lifts conversions per click by +2.80%, and drives +0.98% cumulative improvement in topline metrics.

Related papers

• Amplifying, Not Learning: Fine-Tuned AI Text Detectors Amplify a Pretrained Direction [51.56484100374058]
  Text detectors amplify a pretrained typicality axis; they do not construct an AI-vs-human boundary.<n>On raw encoders before any task supervision, projecting onto centroid(AI)-centroid(HC3) achieves NYT-vs-HC3 AUROC 0.806/0.944/0.834 across three architectures.<n>On RoBERTa-base, raw projection exceeds fine-tuning; on RoBERTa-base, full fine-tuning reduces discrimination below raw on both fluent-formal populations tested.
  arXiv  Detail & Related papers  (2026-05-20T19:08:38Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• On Predicting Post-Click Conversion Rate via Counterfactual Inference [10.398909602421018]
  We propose a method to counterfactually generate conversion labels for non-clicked samples.<n>Our approach is named the Entire Space Counterfactual Inference Multi-task Model (ESCIM)
  arXiv  Detail & Related papers  (2025-10-06T13:57:49Z)
• Improving conversion rate prediction via self-supervised pre-training in online advertising [2.447795279790662]
  Key challenge in training models that predict conversions-given-clicks comes from data sparsity. We use the well-known idea of self-supervised pre-training, and use an auxiliary auto-encoder model trained on all conversion events. We show improvements both offline, during training, and in an online A/B test.
  arXiv  Detail & Related papers  (2024-01-25T08:44:22Z)
• Soft Frequency Capping for Improved Ad Click Prediction in Yahoo Gemini Native [1.9315883475944244]
  Yahoo's native advertising (also known as Gemini native) serves billions of ad impressions daily, reaching a yearly run-rate of many hundred of millions USD. Offset is a one-pass algorithm that updates its model for every new batch of logged data using a gradient descent (SGD) based approach. We propose a soft frequency capping (SFC) approach, where the frequency feature is incorporated into the OFFSET model as a user-ad feature and its weight vector is learned via logistic regression.
  arXiv  Detail & Related papers  (2023-12-08T14:12:49Z)
• Unbiased Filtering Of Accidental Clicks in Verizon Media Native Advertising [1.6717433307723157]
  We focus on the challenge of predicting click-through rates (CTR) when we are aware that some of the clicks have short dwell-time. An accidental click implies little affinity between the user and the ad, so predicting that similar users will click on the ad is inaccurate. We present a new approach where the positive weight of the accidental clicks is distributed among all of the negative events (skips), based on their likelihood of causing accidental clicks.
  arXiv  Detail & Related papers  (2023-12-08T12:54:30Z)
• An Offline Metric for the Debiasedness of Click Models [52.25681483524383]
  Click models are a common method for extracting information from user clicks.<n>Recent work shows that the current evaluation practices in the community fail to guarantee that a well-performing click model generalizes well to downstream tasks.<n>We introduce the concept of debiasedness in click modeling and derive a metric for measuring it.
  arXiv  Detail & Related papers  (2023-04-19T10:59:34Z)
• Will My Robot Achieve My Goals? Predicting the Probability that an MDP Policy Reaches a User-Specified Behavior Target [56.99669411766284]
  As an autonomous system performs a task, it should maintain a calibrated estimate of the probability that it will achieve the user's goal. This paper considers settings where the user's goal is specified as a target interval for a real-valued performance summary. We compute the probability estimates by inverting conformal prediction.
  arXiv  Detail & Related papers  (2022-11-29T18:41:20Z)
• Joint Optimization of Ranking and Calibration with Contextualized Hybrid Model [24.66016187602343]
  We propose an approach that can Jointly optimize the Ranking and abilities (JRC) for short. JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.
  arXiv  Detail & Related papers  (2022-08-12T08:32:13Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.