It is possible to use AutoML to forecast monthly data, but it may require some additional steps or adjustments.
One approach is to resample the monthly data to a lower frequency such as weekly or daily, and then use AutoML to forecast at that lower frequency. Once the forecast is generated, you can then upsample it back to the monthly frequency.
Another approach is to use the AutoML's function auto_timeseries_forecast() to train on your monthly data and then use forecast() function to generate predictions with desired frequency. It is not clear whether Databricks AutoML plans to add support for monthly frequency in the near future, but you can check the documentation and community forum to see if there are any updates or plans. It should be noted that, when working with monthly data, it is important to consider any seasonality and trend patterns that may be present in the data, and make sure that the chosen model is appropriate for your use case.
