Skip to main content

Workflow

API Workflow

The Time Detect API streamlines the management of time and absence registrations through a series of steps. This process, outlined below, ensures efficient data handling from initial upload to model updating.

The core steps are:

  • Upload Historical Data: Submit approved registrations to establish a baseline for model training.
  • Train Models: Use the historical data to train models capable of predicting anomalies in new registrations.
  • Create Predictions: Generate predictions for new registrations based on the trained models.
  • Fetch Results: Retrieve the prediction results to review potential anomalies.
  • Upload New Registrations: Continuously update the system with new registrations.
  • Update Models: Maintain model accuracy by retraining or streaming updates as new data is introduced.

In the next sections we will go through each step in detail.