# PinDCO: Whole-Page Aware Dynamic Creative Optimization at Scale

arXiv: https://arxiv.org/abs/2609.11943 · HTML: https://mlsanity.com/paper/2609.11943/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 20 of 20)

- [NIMA: Neural Image Assessment](https://mlsanity.com/paper/1709.05424/) (2017)
- [Learning to Create Better Ads: Generation and Ranking Approaches for Ad Creative Refinement](https://mlsanity.com/paper/2008.07467/) (2020)
- [A New Creative Generation Pipeline for Click-Through Rate with Stable Diffusion Model](https://mlsanity.com/paper/2401.10934/) (2024)
- [Adversarial Multimodal Representation Learning for Click-Through Rate Prediction](https://mlsanity.com/paper/2003.07162/) (2020)
- [Recommending Themes for Ad Creative Design via Visual-Linguistic Representations](https://mlsanity.com/paper/2001.07194/) (2020)
- [A Hybrid Bandit Model with Visual Priors for Creative Ranking in Display Advertising](https://mlsanity.com/paper/2102.04033/) (2021)
- [Automated Creative Optimization for E-Commerce Advertising](https://mlsanity.com/paper/2103.00436/) (2021)
- [Image Matters: Visually modeling user behaviors using Advanced Model Server](https://mlsanity.com/paper/1711.06505/) (2017)
- [Category-Specific CNN for Visual-aware CTR Prediction at JD.com](https://mlsanity.com/paper/2006.10337/) (2020)
- [Enabling Hyper-Personalisation: Automated Ad Creative Generation and Ranking for Fashion e-Commerce](https://mlsanity.com/paper/1908.10139/) (2019)
- [Algorithmic Copywriting: Automated Generation of Health-Related Advertisements to Improve their Performance](https://mlsanity.com/paper/1910.12274/) (2019)
- [Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure](https://mlsanity.com/paper/2103.01453/) (2021)
- [Visual Encoding and Debiasing for CTR Prediction](https://mlsanity.com/paper/2205.04168/) (2022)
- [Automatic Generation of Product-Image Sequence in E-commerce](https://mlsanity.com/paper/2206.12994/) (2022)
- [Boost CTR Prediction for New Advertisements via Modeling Visual Content](https://mlsanity.com/paper/2209.11727/) (2022)
- [Parallel Ranking of Ads and Creatives in Real-Time Advertising Systems](https://mlsanity.com/paper/2312.12750/) (2023)
- [TSI: an Ad Text Strength Indicator using Text-to-CTR and Semantic-Ad-Similarity](https://mlsanity.com/paper/2108.08226/) (2021)
- [Neural Insights for Digital Marketing Content Design](https://mlsanity.com/paper/2302.01416/) (2023)
- [Hybrid CNN Based Attention with Category Prior for User Image Behavior Modeling](https://mlsanity.com/paper/2205.02711/) (2022)
- [COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation](https://mlsanity.com/paper/2607.08071/) (2026)

## Abstract (arXiv)

Recent advances in generative AI have substantially accelerated the creation of high-quality ad creatives, dramatically expanding the number of candidate variants per campaign. This shift increases the need for scalable dynamic creative optimization (DCO) systems that can match creatives to the most relevant audiences under stringent latency and cost constraints. We present PinDCO, a production DCO system for ad creative retrieval and selection on Pinterest, a billion-scale visual discovery platform. PinDCO is built around a Creative Component Fusion Network (CCFN) that performs dynamic creative scoring by modeling each creative component (e.g., image, title, layout) with a dedicated tower, using component-specific hyperparameters to account for differing modeling complexity. The component representations are fused to predict a creative-level score conditioned on the ad-level prediction, and we improve training data quality via an exploration-exploitation strategy. To account for Pinterest's waterfall grid layout, where a creative's rendered size affects nearby content and session-level engagement, we introduce a Pixel-aware Adjustment Module(PAM) that adjusts scores based on creative size to encourage efficient screen real-estate utilization and better whole-page outcomes. To support the large volume of creative candidates, we further employ a lightweight pre-selection model for early pruning, and optimize serving efficiency through caching and dynamic batching. Extensive offline analyses and online A/B experiments demonstrate the effectiveness of PinDCO, yielding a +3.09% lift in ad Click-Through Rate(CTR) with positive whole-page metrics. With the strong performance, we launched PinDCO in the Pinterest Ads platform.