Using a Parallelized Library on the Cloud for Distributed Time Series Forecasts

Working on forecasting 500,000 time series or even if you're at a business doing something like 15 KPI forecasts that's not really tenable to do manual training and managing and monitoring. Black swan events should be removed from the ingredient forecasting as well as our sales because those might be logged in the data as an order but profit was zero because it was free so it's important to go back and clean that outor else the forecast is going to get confused.