# 安定性

> 安定性 - Use the Stability tab for an at-a-glance summary of how well a model performs on different
> backtests, so you can judge whether a model is consistent across time.

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 `2026-10-09T14:18:51.446191+00:00` (UTC).

## Primary page

- [安定性](https://docs.datarobot.com/ja/docs/workbench/build-workbench/experiments/experiment-insights/stability.html.md): Full documentation for this topic (Markdown sidecar).

## Sections on this page

- [次のステップ](https://docs.datarobot.com/ja/docs/workbench/build-workbench/experiments/experiment-insights/stability.html.md#next-steps): In-page section heading.

## Documentation content

| タブ | 説明 |
| --- | --- |
| パフォーマンス | さまざまなバックテストにおけるモデルのパフォーマンスを一目で把握できるサマリーを提供します。 Time-aware only |

[安定性](https://docs.datarobot.com/ja/docs/classic-ui/modeling/analyze-models/evaluate/stability-classic.html.md) タブは、パフォーマンスを測定するのに役立ち、再トレーニングが必要になるまでのモデルの実稼働期間（「安定」期間）を示します。 チャートの値は、各バックテストとホールドアウトの検定スコアを表します。

## 次のステップ

Continue evaluating your time-aware model's performance across backtests with these related insights.

- Accuracy Over Time : Visualize how prediction accuracy changes over time.
- Period Accuracy : Compute error metric values for specific periods of the backtest validation source.
- Forecasting Accuracy : See a visual indicator of how well the model predicts at each forecast distance.