Scoring / Making Predictions / Inferencing

Ready

What is Scoring?

Scoring, also known as inferencing, is the process of using a trained machine learning model to make predictions based on input data. There are two types of scoring: batch scoring and real-time scoring. Batch scoring involves using the model to make predictions on multiple rows of data. Real-time scoring involves using the model to make predictions on individual rows of data.


In Driverless AI, users can do batch scoring on the new input data by using “Score on Another Dataset” button located in the experiment dashboard. Alternatively, users can download the model object from the experiment dashboard and then develop their own applications for real-time scoring.

Resources

Tutorial

  • Scoring Pipeline Deployment Introduction (link coming soon…)

#scoring
#driverless-ai
#mojo
#concepts
0 comments
3 Views
 

Permalink

Related Links

No Related Resource entered.