Posted On: Nov 19, 2021

We’re excited to announce two new forecasting APIs for Amazon Forecast that generate up to 40% more accurate forecasts and help you understand which factors, such as price, holidays, weather, or item category, are most influencing your forecasts. Forecast uses machine learning (ML) to generate more accurate demand forecasts, without requiring any ML experience. Forecast brings the same technology used at Amazon to developers as a fully managed service, removing the need to manage resources.

With today’s launch of the new CreateAutoPredictor API, Forecast can now forecast up to 40% more accurate results by using a combination of ML algorithms that are best suited for your data. In many scenarios, ML experts train separate models for different parts of their dataset to improve forecasting accuracy. This process of segmenting your data and applying different algorithms can be very challenging for non-ML experts. Forecast uses ML to learn not only the best algorithm for each item, but the best ensemble of algorithms for each item, leading to up to 40% better accuracy on forecasts.

Previously, you would have to train your entire forecasting model again if you were bringing in recent data to use the latest insights before forecasting for the next period. This can be a time-consuming process. Most Forecast customers deploy their forecasting workflows within their operations such as an inventory management solution and run their operations at a set cadence. Because retraining on the entire data can be time-consuming, customer operations may get delayed. With today’s launch, you can save up to 50% of retraining time by selecting to incrementally retrain your AutoPredictor models with the new information that you have added.

Lastly, an AutoPredictor forecasting model also helps with model explainability. To further increase forecast model accuracy, you can add additional information or attributes such as price, promotion, category details, holidays, or weather information, but you may not know how each attribute influences your forecast. With today’s launch, Forecast now helps you understand and explain how your forecasting model is making predictions by providing explainability reports after your model has been trained. Explainability reports include impact scores, so you can understand how each attribute in your training data contributes to either increasing or decreasing your forecasted values. By understanding how your model makes predictions, you can make more informed business decisions. Additionally, using the new CreateExplainability API, Amazon Forecast now provides granular item level explainability insights across specific items and time duration of choice. Better understanding why a particular forecast value is high or low at a particular time is helpful for decision making and building trust and confidence in your ML solutions. Explainability removes the need of running multiple manual analyses to understand past sales and external variable trends to explain forecast results.

To get more accurate forecasts, faster retraining, and model explainability, read our blog or follow the steps in this notebook in our GitHub repo. If you want to upgrade your existing forecasting models to the new CreateAutoPredictor API, you can do so with one click either through the console or as shown in the notebook in our GitHub repo. To learn more, review Training Predictors. To get item level explainability insights, read our blog and follow this notebook in our GitHub repo. You can also review Forecast Explainability or CreateExplainability API.

These launches are accompanied with new pricing, which you can review at Amazon Forecast pricing. You can use these new capabilities in all Regions where Amazon Forecast is publicly available. For more information about region availability, see AWS Regional Services.