mlForecast allows users to apply scikit-learn models, such as random forests or gradient boosting to time series data. This particular implementation uses the hyperopt python package, automatically training numerous sklearn random forest, XGBoost, and LightGBM models, identifying over multiple iterations which parameters perform the best. The results for the champion model are then provided. If trained using CPU, then a maximum of 32 time series will be processed, while if trained using GPU a maximum of 128 will be processed instead, and the maximum iterations used to identify the best models will be higher. Models are trained using all series, meaning that with more series included performance is likely to improve. The seasonality parameter can be altered to reflect known cycles in the data (for example, if hourly data that is expected to vary in a regular pattern over a 24 hour period, then a seasonality of 24 may be suitable).A seasonality of 1 implies that no seasonality is included in the model.

Please provide data in three columns, in the following order:

• unique_id for each time series (up to 32 time series can be provided in one file, and trained simultaneously--if unique_id is not included it is assumed that the file contains only one time series).
• date-time column can be in any format (date, time, number, other), but must be in ascending order.
• value. The value of the time series at each time