Company

Uber

10 cases from Uber (Mobility, Marketplace, Food delivery), each digested from a public talk or engineering post and linked to the original. 3 report results in production.

Tasks: Catch fraud and abuse, Moderate content at scale, Detect anomalies, Build a data platform, Reduce ML cost and 3 more. Methods: Anomaly detection, Rule-based heuristics, Gradient boosting, Time-series forecasting, Feature selection, Fraud scoring and 18 more. Tools: Apache Hive, Apache Kafka, Apache Spark, XGBoost, Prophet, Jira and 2 more.

Tech blog: uber.com