After training a model, if graphs are not showing in the graphs section, it could be due to the following reasons:   For multiple classification models,...

The MAPE calculation is as follows: When you use a separate dataset for hold-out, and in this dataset, under the target feature there is at least one cel...

In linear models, R squared is calculated as 1 − SSE/SST. However, the way we calculate R squared is by using the squared Pearson correlation coefficient a...

You can find the setting for classification thresholds in the prediction section. To view the best threshold determined by Decanter AI, select the "...

It is normal to sometimes get NaN for RMSLE scores. Since log cannot be negative, when a prediction value is negative, RMSLE will be shown as NaN.

This could be due to the following reasons:   Scenario 1: One algorithm was selected but the Number of Models to Train was set to 30.   Explanation: Dec...

The "Merge Column" field is to set up your prediction output based on the columns you selected to merge.  It is recommended to merge the ID co...

After a clustering model is trained, before you start the prediction process, make sure you merge features such as ID, time, and other related features to b...

Here's how the Feature Importance bar graph looks like: Typically, Decanter AI would compute each feature's explainability against the trai...

When making predictions, be aware of the following: 1. When uploading test data, the data file needs to follow the file upload restrictions outlined in ...