Aerosolve is an open-source machine learning library developed by Airbnb, designed for interpretable and human-friendly modeling. Built around sparse, human-intuitive features (like geography, pricing), it supports feature quantization, interaction specification, and rule-based priors—enabling domain experts to contribute directly to model behavior.
Features
- Interpretable sparse feature support (geo, price, categorical)
- Feature quantization and interaction control for better modeling
- Domain-informed priors and rule-based feature engineering
- Supports logistic, regression, ranking, and multiclass models
- Easy-to-read model configuration via human-centric DSL or YAML
- Suitable for search ranking, dynamic pricing, and transparent recommendations
Categories
Machine LearningLicense
Apache License V2.0Follow Aerosolve
Other Useful Business Software
Host LLMs in Production With On-Demand GPUs
Deploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Aerosolve!