# Forecasting Accuracy

> Forecasting Accuracy - Use the Forecasting Accuracy tab as a visual indicator of how well a model
> predicts at each forecast distance in the project's forecast window.

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 `2026-10-09T14:05:25.052880+00:00` (UTC).

## Primary page

- [Forecasting Accuracy](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/fcast-accuracy.html.md): Full documentation for this topic (Markdown sidecar).

## Sections on this page

- [Next steps](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/fcast-accuracy.html.md#next-steps): In-page section heading.

## Related documentation

- [NextGen UI documentation](https://docs.datarobot.com/en/docs/workbench/index.html.md): Linked from this page.
- [Workbench](https://docs.datarobot.com/en/docs/workbench/build-workbench/index.html.md): Linked from this page.
- [Predictive experiments](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/index.html.md): Linked from this page.
- [Evaluate models](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/index.html.md): Linked from this page.
- [Forecast vs Actual](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/fcast-v-actual.html.md): Linked from this page.
- [Period Accuracy](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/period-accuracy.html.md): Linked from this page.
- [Series Insights](https://docs.datarobot.com/en/docs/workbench/build-workbench/experiments/experiment-insights/series-insights.html.md): Linked from this page.

## Documentation content

| Tab | Description |
| --- | --- |
| Performance | Provides a visual indicator of how well a model predicts at each forecast distance in the experiment's forecast window. Time-aware only |

Use Forecasting Accuracy to help determine, for example, how much harder it is to accurately forecast four days out as opposed to two days out. The chart depicts how accuracy changes as you move further into the future. The insight is available for all time series experiments (both single series and multiseries).

For each forecast distance, the points represent:

- Green (Backtest 1): the validation score displayed on the Leaderboard, which represents the validation score of the first (most recent) backtest.
- Blue (All Backtests): the backtesting score displayed on the Leaderboard, which represents the average validation score across all backtests.
- Red (Holdout): the holdout score.

Change the optimization metric from the Leaderboard to change the display.

## Next steps

Continue evaluating time-aware model performance with these related insights.

- Forecast vs Actual : Compare how predictions from different forecast points behave against actuals over time.
- Period Accuracy : Compute aggregate error metric values for specific, important periods within the training dataset.
- Series Insights : Review series clustering information for multiseries projects in charted and tabular format.