嗨@Sampriti。Anand, PlanIQ定价是固定的,和based on the number of expected predictions that will be running each month. Determining the number of expected monthly predictions typically requires a discussion with a customer to better understand the desired outcomes of the forecasting process. To oversimplify... If a customer needs a monthly forecast for 1000 SKUs across 300 different stores, they may need 300,000 forecasts per month. With that said... 1. We're making an assumption that every SKU is sold in every store, and often times that isn't the case. This is something you want to address in a conversation with the business to have a better understanding of the # of forecasts required. 2. Just because we may need forecasts at the SKU*Store level, that does not necessarily mean we are building our forecast models and making predictions at that level. Sometimes the data is very sparse at a granular level and it makes more sense to build forecast models at a higher hierarchical level (i.e. build a forecast model that predicts Product Category x Store) and then disaggregate to the SKU. Figuring out which level to build the forecast models at requires a deeper understanding of the data. Knowing the level is important, because PlanIQ pricing is based on the number of predictions forecast models make, not the final level a forecast ends up at in the planning process. 3. Most of the time we're also building multiple forecast models to make predictions, so we can then determine which model is best at predicting any individual SKU (or category). At the extreme case, if we want to test all 5 models offered in PlanIQ (ARIMA, ETS, Prophet, DeepAR, CNN), we'd be looking at 1.5m predictions per month (1000 SKUs * 300 stores * 5 models). 4. You also want to think about building in a prediction buffer for testing out models. Don't try to back into # of monthly predictions by only accounting for what happens during scheduled production runs. A big part of the value of PlanIQ is your ability to make better predictions by testing different models on your own (it can be a fun exercise too!). Sometimes you don't know which features will add value to your forecast predictions until you test them out. Long winded answer but I hope that is helpful. Figuring out the # of monthly predictions required by a customer is a nuanced process. You don't have to be exact, but hopefully considering some of the things I mentioned above helps get you a decent estimate.
... View more