Here are some terms and definitions for PlanIQ.


Attributes contain categorical information that groups historical data items by their shared characteristics (for example, product category). Attributes aren't numeric. These attributes help PlanIQ discover patterns across similar items.

They often represent item hierarchy elements or business dimensions (such as SKU by store). Attributes are used to generate more accurate forecasts.


Backtest is a standard technique to validate machine-learning models, and they assess forecast model quality. Backtest is a way to check how well your forecast model performed. You can import your backtest results into an Anaplan model.

When given a dataset with historical actuals, the forecast model training mechanism trains itself on a part of the dataset and then tests itself by predicting other parts of the dataset (before unseen). 

Example: Take a historical dataset of 12 months with a forecast horizon of 3 months. PlanIQ trains itself on the first 9 months and then predicts the next 3 months. PlanIQ then compares its 3 month prediction with the actuals from that period.

These steps are how we calculate model accuracy in PlanIQ.

Data collection

A data collection includes historical data, and optionally, related data and attributes. It's used to train forecast models to generate forecast results. 


A forecasting technique where ‌historical data is split out into different components or variables. Each variable in turn, is then used in the forecast. This allows you to assess how much influence a variable has on your forecast.
For example, you might want to see whether the price per unit has less influence on profit than your monthly advertising costs. 

End-of-life item

An end-of-life item is an item PlanIQ assumes is no longer actively used in a forecast, but still exists in the data collection. When an item is identified as end-of-life, a PlanIQ forecast action doesn't generate forecast results for it. An example of an end-of-life item is discontinued merchandise, a product that is no longer sold.

Logic for end-of-life:

PlanIQ counts zero values at the end of the historical data (trailing zeros), for a specific item, and uses this information to determine if the item is end-of-life. One of these must be true:

(1) There are more than 14 trailing zeros for daily data frequency. 

(2) The trailing zeros exceed the forecast horizon. For example:

    • If your forecast horizon is three months.
    • And the last three months of historical data are zero for a specific item.
    • This is true.

(3) PlanIQ counts trailing zeros if:

    • The last three entries for the item are 0. 
    • If the trailing zeros are more than 10% of the total history for the item.
    • Then this item is end-of-life. 

This logic applies to both the Anaplan Prophet and MVLR algorithms. 


Models and methods that make the decisions and behavior of machine learning tools more understandable.

Forecast action

A forecast action generates a prediction from the most recent actuals. The action imports the forecast results and explainability information (for supported algorithms) from PlanIQ into the Anaplan model.

Forecast horizon

The length of time into the future for which the forecast generates predictions. The maximum forecast horizon is set by the depth of historical data and the selected algorithm.

Forecast model

An algorithm trained from a data collection to generate forecasts.

Forecast time interval

The interval for the forecasted data points, as defined by the input data (historical and related), and the selected algorithm. The forecast time interval can be either daily, weekly, or monthly.

Historical data (actuals)

The primary data type used in a forecast. This data is mandatory. It must be numerical and include a time dimension. Examples: Units sold, Expenditure.


A parameter whose value is used to control the learning process of the forecast model. Hyperparameter tuning is part of the model configuration procedure within PlanIQ.


The number of historical time periods used to forecast a future time period. For example, PlanIQ needs three months of historical data (March, April, May) to calculate a trend for June. Similarly, to obtain a single yearly trend datapoint for March 2021, PlanIQ needs 12 months of historical data from March 2020 to March 2021. 


Also known as residuals, noise is where data points deviate from the forecasting trend. In time series forecasting, noise is unpredictable random data that deviates from the typical behavior of the time series. Noise can be a useful indicator of model quality.

Related data (drivers)

An optional dataset that provides additional drivers (business factors and values) to your forecast. Related data can help PlanIQ improve forecast accuracy. Examples are historical data and forward-looking promotions. Related data include:

  • A time dimension (for example: historical and forward-looking promotions). 
  • Historical data points leading up to the forecast horizon. 
  • Future data points to cover the length of the forecast horizon (optional but recommended for increased forecast accuracy).  

Sparse data 

A dataset where many of the values are 0. For example, if your dataset represents demand for a product over time, and there are periods where demand is zero.

Before you include a dataset in a data collection, you can choose to distinguish between true zeros and zeros that represent missing data. This distinction helps ensure that your forecast results aren't skewed. For more information, see Exclude values.

Time series

A sequence of successive data points (observations) in time, that occur at regular time intervals.

Time series forecasting

Prediction of a time series’ future values based on historical and other data types.