# Looper: An end-to-end ML platform for product decisions

arXiv: https://arxiv.org/abs/2110.07554 · HTML: https://mlsanity.com/paper/2110.07554/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 61 references that are in the map.
- First posted on arXiv 14 Oct 2021.

## Builds on (most cited first, 22 of 22)

- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning](https://mlsanity.com/paper/1706.03461/) (2017)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [The Case for Learned Index Structures](https://mlsanity.com/paper/1712.01208/) (2017)
- [Challenges in Deploying Machine Learning: a Survey of Case Studies](https://mlsanity.com/paper/2011.09926/) (2020)
- [Parallel Bayesian Optimization of Multiple Noisy Objectives with Expected Hypervolume Improvement](https://mlsanity.com/paper/2105.08195/) (2021)
- [Constrained Bayesian Optimization with Noisy Experiments](https://mlsanity.com/paper/1706.07094/) (2017)
- [PyTorch Distributed: Experiences on Accelerating Data Parallel Training](https://mlsanity.com/paper/2006.15704/) (2020)
- [The Architectural Implications of Facebook's DNN-based Personalized Recommendation](https://mlsanity.com/paper/1906.03109/) (2019)
- [Horizon: Facebook's Open Source Applied Reinforcement Learning Platform](https://mlsanity.com/paper/1811.00260/) (2018)
- [Beyond One-hot Encoding: lower dimensional target embedding](https://mlsanity.com/paper/1806.10805/) (2018)
- [Ludwig: a type-based declarative deep learning toolbox](https://mlsanity.com/paper/1909.07930/) (2019)
- [Overton: A Data System for Monitoring and Improving Machine-Learned Products](https://mlsanity.com/paper/1909.05372/) (2019)
- [Bayesian Optimization for Policy Search via Online-Offline Experimentation](https://mlsanity.com/paper/1904.01049/) (2019)
- [Designing and Deploying Online Field Experiments](https://mlsanity.com/paper/1409.3174/) (2014)
- [Real-world Video Adaptation with Reinforcement Learning](https://mlsanity.com/paper/2008.12858/) (2020)
- [Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints](https://mlsanity.com/paper/1911.00638/) (2019)
- [Managing ML Pipelines: Feature Stores and the Coming Wave of Embedding Ecosystems](https://mlsanity.com/paper/2108.05053/) (2021)
- [Declarative Machine Learning Systems](https://mlsanity.com/paper/2107.08148/) (2021)
- [Personalization for Web-based Services using Offline Reinforcement Learning](https://mlsanity.com/paper/2102.05612/) (2021)
- [Predictive Precompute with Recurrent Neural Networks](https://mlsanity.com/paper/1912.06779/) (2019)
- [Evaluation of Explore-Exploit Policies in Multi-result Ranking Systems](https://mlsanity.com/paper/1504.07662/) (2015)

## Built on by (most cited first, 9 of 9)

- [MCGrad: Multicalibration at Web Scale](https://mlsanity.com/paper/2509.19884/) (2025)
- [Scalable End-to-End ML Platforms: from AutoML to Self-serve](https://mlsanity.com/paper/2302.14139/) (2023)
- [Practical Knowledge Distillation: Using DNNs to Beat DNNs](https://mlsanity.com/paper/2302.12360/) (2023)
- [Efficient Multi-stage Inference on Tabular Data](https://mlsanity.com/paper/2303.11580/) (2023)
- [SmartChoices: Augmenting Software with Learned Implementations](https://mlsanity.com/paper/2304.13033/) (2023)
- [On a Scale-Invariant Approach to Bundle Recommendations in Candy Crush Saga](https://mlsanity.com/paper/2408.06799/) (2024)
- [Experimentation, deployment and monitoring Machine Learning models: Approaches for applying MLOps](https://mlsanity.com/paper/2408.11112/) (2024)
- [Development of an End-to-end Machine Learning System with Application to In-app Purchases](https://mlsanity.com/paper/2412.12390/) (2024)
- [Scalability and Maintainability Challenges and Solutions in Machine Learning: Systematic Literature Review](https://mlsanity.com/paper/2504.11079/) (2025)

## Abstract (arXiv)

Modern software systems and products increasingly rely on machine learning models to make data-driven decisions based on interactions with users, infrastructure and other systems. For broader adoption, this practice must (i) accommodate product engineers without ML backgrounds, (ii) support finegrain product-metric evaluation and (iii) optimize for product goals. To address shortcomings of prior platforms, we introduce general principles for and the architecture of an ML platform, Looper, with simple APIs for decision-making and feedback collection. Looper covers the end-to-end ML lifecycle from collecting training data and model training to deployment and inference, and extends support to personalization, causal evaluation with heterogenous treatment effects, and Bayesian tuning for product goals. During the 2021 production deployment Looper simultaneously hosted 440-1,000 ML models that made 4-6 million real-time decisions per second. We sum up experiences of platform adopters and describe their learning curve.