Monument Introduces Model Serving Capabilities

2 min readNov 2, 2020


Quickly build production-ready Machine Learning workflows with model serving.

NEW YORK, N.Y. — Monument is pleased to announce the roll out of “model serving” capabilities. Model serving enables users to train algorithms on historical data, save the parameterized model, and deploy this model on new data that the model has not previously seen.

Model serving complements the “training” and “validation” steps in the Machine Learning workflow. It is used for two principal workflows: “testing” and “live:”

  1. In testing, the new data contains the values of the target column that is being predicted. The prediction generated by the “served” model can be compared to the known values to assess the accuracy of the model.
  2. In live, the new data does not contain the values of the target column — this is prediction of entirely unknown values.

Applications for model serving functionality include:

  • Price prediction,
  • Fraud detection, and
  • Retail demand forecasting.

The introduction of model serving represents a significant step forward for Monument, allowing for trained models to be re-applied to new data. Further, it is of particular interest to organizations that wish to use and improve trained models over time as new data becomes available. Predictive models can now be dynamically improved over time.

Interested in learning more about Monument? Book a free introductory Zoom call here.