ML Cool - How to Develop Models for Forecasts

How would you think about developing these types of models for something like 15 KPI forecasts versus 500,000 time series forecasts for 15? I'd probably err on the side of accuracy so because I've built enough of them in my time doing this this profession I'd probably start with stats models. You're gonna do better than profit does and PMD ARIMA if you really understand your data set and you understand the stability of variants over time within your data set it's just not tenable could one person maintain that level of automated prognosis.