TIM Anomaly Detection is comprised of three different capabilities:

  • Model building - First, a model has to be built on historical data.
  • Running detection with 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 so that it is adapted to the new dynamics of the underlying process.


Each of them require data as an input. Read more about the data properties that should be met in order to run TIM correctly. There is also a list of all possible configuration parameters that can enter the TIM Anomaly Detection engine. Finally, you can go through the list of all available outputs.