デプロイ設定¶
デプロイを作成して設定したら、個々の機能の設定タブを使用して、デプロイ機能を追加または更新することができます。
トピック | 説明 |
---|---|
サービスの正常性のモニタリングを設定 | Enable segmented analysis to assess service health, data drift, and accuracy statistics by filtering them into unique segment attributes and values. |
データドリフトのモニタリングを設定 | Enable data drift monitoring on a deployment's Data Drift Settings tab. |
精度のモニタリングを設定 | Enable accuracy monitoring on a deployment's Accuracy Settings tab. |
公平性のモニタリングを設定 | Enable fairness monitoring on a deployment's Fairness Settings tab. |
信頼性ルールの設定 | Enable humility monitoring by creating rules which enable models to recognize, in real-time, when they make uncertain predictions or receive data they have not seen before. |
再トレーニングの設定 | Enable Automated Retraining for a deployment by defining the general retraining settings and then creating retraining policies. |
チャレンジャーの設定 | Enable challenger comparison by configuring a deployment to store prediction request data at the row level and replay predictions on a schedule. |
予測設定の確認 | デプロイの推論データの詳細を確認するには、[予測設定]タブを参照します。 |
データ探索を有効にする | Enable data exploration to export deployment data, allowing you to compute and monitor custom business or performance metrics. |
カスタム指標監視の設定 | Enable custom metrics monitoring by defining the "at risk" and "failing" thresholds for the custom metrics you created. |
適時性追跡の設定 | Enable timeliness tracking on a deployment's Usage Settings tab to reveal when deployment status indicators are based on old data. |
時系列デプロイの予測間隔の設定 | Enable prediction intervals in the prediction response for deployed time series models. |