1. PlanIQ
  2. PlanIQ glossary

Here are some terms and definitions for PlanIQ.


This dataset groups products and service items into categories. For example, items can be grouped by regions, styles, or colors. Attributes help PlanIQ identify similar behaviors across items that share similar characteristics.


Backtesting is a standard technique used to validate ML and time series forecasting models. Historical data is split into a train set and a test set. The train set is used to train a forecast model and produce forecasts for the timeframe represented in the test set. The forecast model is then evaluated by comparing the forecasts from the test set to the actuals, or known observed values. This process is known as Backtesting.

The backtest time period used, is equal to the forecast horizon. The model training process withholds historical data for this period and then uses the same period to generate forecasts.

Backtesting results are used to assess forecast model quality.

Data collection

Data collections contain historical data, and if used, supporting datasets, that are used by a forecast model. The forecast model analyzes patterns in the data collection and learns from them. 


A forecasting technique where the 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. 


One or more time-series numerical variables that correlate with or sometimes affect the forecasted time series. Examples might include a competitive sales price per unit, or the number of product promotions.

Forecast action

An action that generates forecasts using a pretrained forecast model. The action imports the results into an Anaplan model. Forecast actions can run on demand or on a schedule.

Forecast horizon

The length of time into the future that the forecast generates predictions for. 

The maximum forecast horizon depends on the length of the historical data and the selected algorithm. For example, if the historical data is actuals from the last 3 months, the forecast horizon predicts up to 3 months ahead.

Forecast model

An algorithm trained by a data collection to generate your forecasts.

Forecast time interval

The frequency of the predictions applied to the forecast. The frequency is taken from the time scales used in the data collection setup (that is, from the historical and related datasets). 

The forecast time interval can be either daily, weekly, or monthly. For example, the forecast predicts that every week you’ll sell 1000 units for the next 4 months (4 months being your forecast horizon).

Historical data (actuals)

A set of numerical data that includes a time scale, that happened in the past. The time scale indicates the actuals produced per day, or week, or month. This is called time series data. 

Historical data is mandatory and is treated as the main data source to base a forecast on. For example, the number of units sold of your company’s products over the past 2 years.


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 3 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 twelve months of historical data from March 2020 to March 2021. 


Also known as residuals, noise is where some 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 

A set of numerical data that includes a time scale and relates to the items that are used to generate a forecast. This data is optional, and helps improve the accuracy of a forecast. 

Related data includes historical data points leading up to the forecast horizon, and future data points to cover the length of the forecast horizon. For example, an upcoming calendar of events, or upcoming marketing promotions. 

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 ensures your forecast result is not skewed. For more information, see Exclude values.

Time series

A sequence of successive data points (observations) in time, recorded at regular time intervals.
For example, the number of sales per month over a six-month period.

Time series forecasting

The prediction of future values for a time series that's based on historical data and other data types.


We may update our documentation occasionally, but will only do so in a way that does not negatively affect the features and functionality of the Anaplan service.