predictedRiskTrainEvalHistory

Tracks the training and evaluation history of predictive risk models used for financial and operational analysis.

Columns


Name	Type	References	Description
nkey [KEY]	Integer		A unique internal identifier assigned to the record, used for tracking and referencing the entry within the system.
accuracy	Decimal		The accuracy of the prediction or model, typically represented as a percentage, indicating how well the model's outputs match the expected results.
bretrained	Boolean		Indicates whether the prediction model has been trained, used to track if the model is ready for making predictions.
defaultname	String		The default name associated with the prediction type, used to identify and categorize the specific prediction model or method being applied.
evaldate	Date		The date when the evaluation of the model or prediction was performed, used for tracking and reporting model performance over time.
mae	Decimal		The Mean Absolute Error (MAE), a metric that measures the average magnitude of errors in a set of predictions, used to assess model performance.
r2	Decimal		The R-Squared (R²) value, a statistical measure of how well the regression model fits the data, representing the proportion of variance explained by the model.
rmse	Decimal		The Root Mean Square Error (RMSE), a measure of the differences between predicted and observed values, used to evaluate the accuracy of the model.