Predictions are generated by running ML_PREDICT_ROW or ML_PREDICT_TABLE on trained models. The row or table of data must have the same feature columns as the data used to train the model. If the target column exists in the data to run predictions on, it is not considered during prediction generation.

ML_PREDICT_ROW generates predictions for one or more rows of data. ML_PREDICT_TABLE generates predictions for an entire table of data and saves the results to an output table.