# What is time-aware modeling?

> What is time-aware modeling? - Use OTV when your data is time-relevant but you are not forecasting;
> use time series when you want to forecast multiple future values; use nowcasting to determine an
> unknown current value of a time series.

This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context.

Companion generated at `2026-04-24T16:03:56.616689+00:00` (UTC).

## Primary page

- [What is time-aware modeling?](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html): Full documentation for this topic (HTML).

## Sections on this page

- [Why use it?](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#why-use-it): In-page section heading.
- [Time series overview](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#time-series-overview): In-page section heading.
- [Supervised learning models](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#supervised-learning-models): In-page section heading.
- [Supervised learning in time-aware mode](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#supervised-learning-in-time-aware-mode): In-page section heading.
- [Try it](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#try-it): In-page section heading.

## Related documentation

- [Classic UI documentation](https://docs.datarobot.com/en/docs/classic-ui/index.html): Linked from this page.
- [Modeling](https://docs.datarobot.com/en/docs/classic-ui/modeling/index.html): Linked from this page.
- [Time-series modeling](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/index.html): Linked from this page.
- [date/time partitioning](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-adv-modeling/ts-date-time.html): Linked from this page.
- [Time series](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-flow-overview.html): Linked from this page.
- [Multiseries](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/multiseries.html): Linked from this page.
- [Segmented](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-segmented.html): Linked from this page.
- ["Nowcast"](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/nowcasting.html): Linked from this page.
- [forecasting](https://docs.datarobot.com/en/docs/reference/glossary/index.html): Linked from this page.
- [OTV specialized workflow](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/otv.html): Linked from this page.
- [validation](https://docs.datarobot.com/en/docs/reference/pred-ai-ref/data-partitioning.html): Linked from this page.

## Documentation content

# What is time-aware modeling?

> [!NOTE] Availability information
> Contact your DataRobot representative for information on enabling time series modeling.

DataRobot offers two mechanisms for time-aware modeling—time series and OTV—both of which are implemented using [date/time partitioning](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/ts-adv-modeling/ts-date-time.html):

- Use the following types oftime seriesmodeling when you want to:
- Useout-of-time validation (OTV)when your data is time-relevant but you are notforecasting(instead, you are predicting the target value on each individual row). "How do I interpret this housing data?" This type of time-aware modeling is described in theOTV specialized workflowsection.

> [!NOTE] Note
> See below for more specific information on [reasons to use time-aware modeling](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#why-use-it) and how to put it in context with [supervised learning](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#supervised-learning-models). Follow the [suggested reading path](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/index.html) to help locate the documentation appropriate to your understanding and requirements.

## Why use it?

People frequently use time-aware models to predict future events while training those models on past data. A major difference between time-aware and conventional modeling is in how validation data—used to judge performance—is selected. For conventional modeling it is common practice to select rows from the dataset for [validation](https://docs.datarobot.com/en/docs/reference/pred-ai-ref/data-partitioning.html), without regard to their time period. This practice is modified for time-aware modeling, to prevent validation scores that are overly optimistic and misleading (and potentially lead to damaging conclusions and actions). Time-aware modeling does not assume that the relationship between predictors and the target is constant over time.

A simple example: Let’s say you want to forecast housing prices. You have a variety of data about each house in your dataset and plan to use that data to predict the sales price. You will build a model using some of the data and make predictions using other parts of the data. The problem is, randomly selecting sale prices from your dataset suggests you are randomly selecting across time as well. In other words, the resulting model doesn't predict the future from the past. Using time-aware modeling, you can train and test models using time-based folds, which assures that your models are always validated on future house price data (the purpose of your forecast). It isn’t necessary to use the most recent data to make predictions—only to use data that is more recent than the data used for model training—to ensure that model predictions about the future hold up.

With time-aware modeling, you think of data in terms of time. When determining how much data you need to build an accurate model, the answer, for example, is in days or months or most recent x number of rows. “How long of a data history will I need and how much will my model improve with more time?” DataRobot partitions the data so that it can evaluate models with an awareness of the data’s time component, providing:

- Improved performance through better model selection
- More accurate validation scores
- Improved support for date variables as predictors

## Time series overview

When working with time series data, ask yourself: How long do I want to look into the past and how far into the future do I want to predict? Once you determine those answers, you can configure DataRobot so that your time-sensitive data uses advanced DataRobot modeling techniques to create forecasts from your data. (See also the section on [why to use time series modeling](https://docs.datarobot.com/en/docs/classic-ui/modeling/time/whatis-time.html#why-use-it).

DataRobot automatically creates and selects time series features in the modeling data. You can constrain the features (for example, minimum and maximum lags, etc.) by configuring the time series framework on the Start screen. Based on your settings and the analysis of the raw dataset, DataRobot derives new features and creates a modeling dataset. Because time shifts, lags, and features have already been applied, DataRobot can use general machine learning algorithms to build models with the new modeling dataset.

## Supervised learning models

In conventional supervised learning, you work with raw training data—with labels or features. DataRobot trains models to predict a specified target based on those features. DataRobot creates a model, tunes it, and then tests it on unseen (out-of-sample) data. That test results in a validation score which can be considered a measure of confidence in how ready the model is for deployment. Once deployed, you can score new data with the model. Feed the new data into DataRobot, where the application extracts features from the data and feeds them into the model. The model then makes predictions on those features to provide information about the target.

When DataRobot trains a model, it makes some decisions based on the training data. By making assumptions about the function or the data, for example, DataRobot can estimate parameter values based on those assumptions. Different modeling approaches make different assumptions. DataRobot's large repository of available models exercises many different functions (aspects), allowing you to pick the model type that best suit the data.

### Supervised learning in time-aware mode

Supervised learning assumes that training examples are independent and identically distributed (IID). That kind of modeling makes predictions based on each row of the dataset, without taking the neighboring rows into account. The assumption is that training samples are independent of each other. Another problematic assumption with the supervised learning is that the data you train on and your future will have the same distribution.

With time-dependent data, the traditional machine-learning assumptions don't work. Consider Google search trends for the term "DataRobot" in the period of July through November, 2017. The search interest is fairly uniform:

If you check the same search trend across the life of DataRobot, you can notice that the time series behaves very differently toward the more recent dates. If you trained a model on the earlier data, say 2013-2016, the model will be ineffective since the data does not follow the same distribution.

## Try it

The table below lists videos available on YouTube that show how to accomplish the necessary tasks using the DataRobot interface and the Python API in a DataRobot Notebook. Follow along in each tutorial by first downloading the sample dataset:

[Download Dataset](https://datarobot-doc-assets.s3.us-east-1.amazonaws.com/Car_Sales_Tutorial_SingleSeries_Multivariate.csv)

| Watch | To learn |
| --- | --- |
| Data structures | The data structures used with time series modeling. The video shows how to structure your time series dataset for univariate, multivariate, and multiseries/multivariate problems. |
| Project settings | How to configure initial project settings and modifying default configurations to suit your experimentation needs. |
| Feature engineering | How to interpret and use DataRobot time series automation outputs, specifically features, feature lists, and Leaderboard models. Specifically, it shows you how to look at time series features and feature lists, and determine how to organize and understand models on the Leaderboard. |
| Model insights | To interpret the performance of a time series model and understand what patterns it has identified in your data. The video focuses on the insights and visualizations associated with each Leaderboard model and identifies important features in the top-performing model. |
| Model deployment | How to select a Leaderboard model and deploy it to a DataRobot Prediction Server. |
| Time series predictions | How to use a production time series model for predictions, including the correct structure for the prediction request file. |