Company

Positive Technologies

5 cases from Positive Technologies (General), each digested from a public talk or engineering post and linked to the original. 2 report results in production.

Tasks: Detect anomalies, Catch fraud and abuse, Moderate content at scale, Evaluate models, Learn user and item embeddings. Methods: Collaborative filtering, Random forest, Gradient boosting, SVM, Markov chains / HMM, Rule-based heuristics and 13 more. Tools: MLflow, CatBoost, LightGBM, ONNX, SHAP and 3 more.