Overview

By reading this section of the documentation you should understand how the TIM Anomaly Detection solution is designed and how it should be used for anomaly detection.

The TIM Anomaly Detection is comprised of three lifecycle methods:

  • Model building - First, a model has to be built on historical data.
  • Running detection with an existing model - Once a model is built it can be repeatedly evaluated in production to detect anomalies on new data that are collected.
  • Rebuilding an existing model - In some cases, it is essential to rebuild the model with more recent data after some period of time to adapt to the new dynamics of the underlying process.

You can learn more about what is happening under the hood of the TIM Anomaly Detection engine when building a model in the Engine schema subsection.

See also What problems TIM AD can solve subsection to read more about what types of problems are suited for TIM Anomaly Detection.