What is 'model fit' in SAP CEC-MKT-ML-PRE - Predictive Studio?

model fit - Overview

• Component: CEC-MKT-ML-PRE

• Component Name: Predictive Studio

• Description: A predictive model that has been trained on a specified set of training data, using one statistical method.

model fit - Details

• 
  Key Concepts: 
  Model fit is a measure of how well a predictive model fits the data it is trained on. It is used to evaluate the accuracy of a model and determine whether it is suitable for use in a given situation. In SAP Predictive Studio, model fit is measured using the Root Mean Squared Error (RMSE) metric. 
  
  How to use it: 
  In SAP Predictive Studio, model fit can be evaluated by running the model on a test dataset and comparing the predicted values to the actual values. The RMSE value will be displayed in the output of the model, and can be used to determine how well the model fits the data. 
  
  Tips & Tricks: 
  When evaluating model fit, it is important to consider both the RMSE value and the distribution of errors. If the errors are distributed evenly across all values, then this indicates that the model is performing well. However, if there are large errors for certain values, then this indicates that the model may not be suitable for use in that situation. 
  
  Related Information: 
  For more information on evaluating model fit in SAP Predictive Studio, please refer to the official documentation here: https://help.sap.com/viewer/product/CEC-MKT-ML-PRE/Cloud/en-US/f9f8d7a3e2b14c8a9f3d7c2b6d5f9a4e.html