Choose this use-case if you wish to develop a model that forecasts cumulative values for a metric such as revenue, cash flow, or sales. Cumulative forecasting is especially useful in scenarios where you are interested in the total accumulation of a quantity over a period of time rather than the quantity at a specific point in time. Given a dataset of time-series values corresponding to the target metric and an optional secondary dataset of all relevant item attributes, you can generate a model that generates predictions about that metric in a future time window. This model will learn from all available product data, SKUs, and salesperson profiles to generate accurate forecasts that allow for efficient resource allocation and spend.
Dataset and Feature Group RequirementsThis section specifies the Datasets / Feature Groups requirements to successfully train a Cumulative Forecasting model. Feature requirements include recommendations on additional datasets that might enhance model performance.
Training Models - Training Options and MetricsThis section describes all the available model training options that can be used to create a Cumulative Forecasting model. You can utilize the metric explanations to better understand how they measure the performance of the model you trained.
Evaluating PredictionsThis section contains a quick model evaluation guide that helps you understand how well your model is performing.
Prediction APIThis section discusses the prediction API method so that you could properly generate predictions from the model you deployed.