PlanIQ supports a number of industry-wide algorithms that you can apply to your datasets to make predictions.
This page provides information on the properties each of the different algorithms contain to help you decide which one to use for your forecast.
Your feedback is important to us. To ensure you have a good content experience, we'd appreciate if you could tell us how you find the guidance on this page and if it addresses your questions.
To take part, complete the quick survey at the end of the article, and tell us how we can improve.
We recommend you use this information to help you select an algorithm that best suits your data collection and the type of predictions you want to generate.
PlanIQ supports the following algorithms:
Anaplan AutoML chooses the best algorithm for your forecast, based on the properties in your dataset. Anaplan AutoML executes all Amazon Forecast algorithms. This includes the different variants of DeepAR+ with different hyper parameter configurations.
PlanIQ compares MAPE (mean absolute scaled error) results for every individual item for every algorithm that is executed. It then chooses the algorithm that provides the best MAPE result for the majority of the items. This algorithm is used for the forecasts.
To summarize, Anaplan AutoML chooses the algorithm that is the best for the majority of items in the data collection. This is rather than for every item in the data collection.
For example, in a data collection with 10 items, Anaplan AutoML picks the algorithm that provides the best MASE result for the majority of items.
Based on MASE, Algorithm A provides a good forecast for three items, and Algorithm B provides a good forecast for eight items. The engine chooses Algorithm B as it provides a better performance for the majority of the items.
Amazon Forecast AutoML
Amazon Forecast checks all of the Amazon algorithms and applies the most suitable one for your entire dataset. Amazon Forecast AutoML selects an algorithm that provides the best prediction performance. This is based on an assessment of the performance at P10, P50, and P90 quantiles for the entire data collection.
This is a Convolutional Neural Network - Quantile Regression model for large datasets. It's the only algorithm that accepts related data with or without forward-looking information. The algorithm also accepts attributes.
This is a recurrent neural networks (RNN) model for large data sets. It works with related data that has forward-looking information and attributes.
This is an Exponential Smoothing algorithm. Use for small datasets with seasonality.
Note: We recommend you use a different algorithm for datasets that have a weekly time scale and yearly seasonal patterns.
This is an Autoregressive Integrated Moving Average algorithm. It's a statistical model useful for datasets that can be mapped to stationary time series. Use for small datasets.
This is an additive regression model. Use for scenarios that involve seasonality and outliers. It works with related data that has forward-looking information.
CNN-QR and DeepAR+ are global algorithms. They're looking not only at individual time series in order to predict it, but also learning from other time series from the same dataset. This is particularly useful in cases where multiple time series share similar behaviors.
Here is a summary of the technical differences between the individual algorithms:
|Able to use related time series||Yes||Yes||Yes||-||-|
|Able to use related time series without forward looking information||Yes||-||-||-||-|
|Able to use item metadata||Yes||Yes||-||-||-|
|Suitable for sparse datasets||Yes||Yes||-||-||-|
|Suitable for what-If analysis||Yes||Yes||Yes||-||-|
|Suitable for cold-start scenarios||Yes||Yes||-||-||-|
|The forecast model is updated with every prediction||-||-||Yes||Yes||Yes|
|The forecast model needs to retrain to incorporate new actuals into the model itself||Yes||Yes||-||-||-|