Tool

LightGBM

36 cases from 24 companies use LightGBM in their stack. 7 were checked in an online A/B test; 15 report results in production. Tasks: Retrieve and rank from millions of items, Optimize decisions, Forecast demand and load, Predict churn and lifetime value and 14 more. Methods: Gradient boosting, SHAP, Rule-based heuristics, Learning to rank, LLM-as-a-judge and 100 more. Companies: DoorDash, Avito, Lyft, Expedia Group, Etsy, Airbnb and 18 more.

Agentic Feature Engineering: How McAfee Drives Personalization With Agent Bricksgeneral2026-06
How Mastercard Turns Transaction Data into Trusted Merchant Insights with AIfintech2026-06
Winner's Solution Walkthrough: 2nd Place (AvitoTech ML Cup 2026)classifieds2026-05
How Vinted Serves Personalised Search Autocompletemarketplace2026-04
Reducing experiment duration with predicted control variatese-commerce2025-11
My Starter Project on the Lyft Rider Data Science Teammobility2025-10
How We Grew Sales Team Efficiency with Customer Rankingclassifieds2025-05
Cold-Starting Sales of Complementary Products with LLMsfood-delivery2025-05
Does High Click-through Rate Lead to High Conversion Rate?travel2025-05
How Airbnb measures Listing Lifetime Valuetravel2025-03
Using LLM to transcribe restaurant menu photosfood-delivery2025-03
Single AI View of Customer: A retailers guide to Know Your Customer Better using Customer Embeddings and Customer Personaretail2025-03
Challenges of ML Development in an Expert Domain Requiring High Accuracygeneral2024-11
Predictive Modeling for Availability of Inventoryretail2024-10
Beyond the Click: Elevating DoorDash's personalized notification experience with GNN recommendationfood-delivery2024-06
Developing a Recommender System for Ammonia Productionmanufacturing2024-05
Classic Is All You Need! Selecting Reply Templates for Customer Requestsgeneral2024-05
Multimodal Geo Embeddings: Methods, Results and Deploymentbanking2024-05
Neural Network Architectures in Credit Scoring—banking2024-05
Predicting Individual Churn Periods of Users, or Unexpected Properties of Quantile Regression in Marketing Taskse-commerce2024-05
Product Features: The Key to Increasing Model Efficiency for Account Propensitysaas-b2b2023-10
End-to-end Keyword Bidding for Apple Search Adsadtech2023-09
The Juggler Model: Balancing Expectations in Lodging Rankingstravel2023-09
The Recommendation System at Lyftmobility2023-08
How DoorDash Built an Ensemble Learning Model for Time Series Forecastingfood-delivery2023-06
How to Build Real-Time ML at a Crypto Exchangefintech2023-05
Beyond global sentiment: object, aspect sentiments—general2023-05
Lifecycle of a Successful ML Product: Reducing Dasher Wait Timesfood-delivery2023-02
How DoorDash Upgraded a Heuristic with ML to Save Thousands of Canceled Ordersfood-delivery2023-01
What is good for a doctor is death for an engineer: extra requirements for medical AI services—healthtech2022-10
Evolving DoorDash's Substitution Recommendations Algorithmfood-delivery2022-09
Optimizing Markdown in Fashion E-Commerce with Machine Learninge-commerce2022-08
Active Learninghealthtech2022-06
Modernizing Nextdoor Search Stack — Part 2social2022-05
Building the Model Behind DoorDash's Expansive Merchant Selectionfood-delivery2022-04
How Zomato built and deployed a cheap, accurate delivery-partner ETA modelfood-delivery2022-03