Method
Autoencoder anomaly detection
Flagging anomalies by reconstruction error.
6 cases from 5 companies apply Autoencoder anomaly detection.
Typical tasks: Detect anomalies, Catch fraud and abuse, Moderate content at scale. Companies: Grab, LinkedIn, Celsus, Netflix and 1 more. Often combined with: Gradient boosting, Isolation Forest, LSTM, Weak supervision, Outlier handling and 19 more.
Virtual Flow Metering: Forecasting Oil Production with Machine Learning![]() | ![]() | manufacturing | 2025-05 |
| ML in Predicting ESP Failures | — | manufacturing | 2024-05 |
| Unsupervised graph anomaly detection - Catching new fraudulent behaviours | food-delivery | 2023-08 | |
| New Approaches For Detecting AI-Generated Profile Photos | social | 2023-06 | |
Data-Centric AI: A Review of Methods![]() | ![]() | healthtech | 2023-05 |
| Machine Learning for Fraud Detection in Streaming Services | media-streaming | 2022-09 |

