{"templateId":"markdown","sharedDataIds":{"sidebar":"sidebar-@l10n/ja/sidebars.yaml"},"props":{"metadata":{"markdoc":{"tagList":["admonition"]},"type":"markdown"},"seo":{"title":"予測モデルの作成","description":"Audience Studioで予測モデルを作成する手順を解説。機械学習を活用し、セグメントのターゲティングを最適化する方法を詳しく説明します。","siteUrl":"https://docs.treasure.ai","lang":"en-US","jsonLd":{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://www.treasure.ai/","name":"Treasure AI","url":"https://www.treasure.ai/","logo":"https://www.treasure.ai/hubfs/assets/images/logos/primary-logo.svg"},{"@type":"WebSite","@id":"https://docs.treasure.ai/#website","name":"Treasure AI Documentation","url":"https://docs.treasure.ai/","inLanguage":["en","ja"],"publisher":{"@id":"https://www.treasure.ai/"}}]}},"dynamicMarkdocComponents":[],"compilationErrors":[],"ast":{"$$mdtype":"Tag","name":"article","attributes":{},"children":[{"$$mdtype":"Tag","name":"Heading","attributes":{"level":1,"id":"予測モデルの作成","__idx":0},"children":["予測モデルの作成"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["予測モデルを作成して、セグメントのターゲティングを改善します。"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Safariは予測モデルの一部の機能をサポートしていません。"]},{"$$mdtype":"Tag","name":"Heading","attributes":{"level":1,"id":"予測モデルの定義","__idx":1},"children":["予測モデルの定義"]},{"$$mdtype":"Tag","name":"ol","attributes":{},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Treasure コンソールを開きます。"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Audience Studio"]},"に移動します。"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["ペアレントセグメントを選択します。例:"," ",{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_13-25-22.81ad73efcae1deb4249e036183812042f3d8136a570121cee40cc4e156f807cd.cf3845cb.png","alt":""},"children":[]}]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["表示されたペアレントセグメントをそのまま使用するか、別のセグメントを選択します。"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Create New"]},"を選択します。"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Predictive Model"]},"を選択します。"," ",{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_10-49-52.efa1243525b0ec462eacd041e65c5b06e8b3f53554f7e8b3ca07a0574d5dc3d5.cf3845cb.png","alt":""},"children":[]}]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["モデルに名前を付けます。"]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Next"]},"を選択します。"," ",{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_13-58-47.7e0973eaa78d48efbe1a9ca628534e78a03570f4520384b23624945cc5caac5c.cf3845cb.png","alt":""},"children":[]}]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["トレーニング母集団を選択します。"," ","これは、Treasure Dataの機械学習のトレーニングプロセスで使用するサンプルデータセットです。このデータセットは、高度な結果を生成するために使用されます。データセットは、セグメントまたはペアレントセグメント内のすべてのプロファイルにすることができます。"," ","ファネルステージは、トレーニング母集団、スコアリングターゲット、またはポジティブサンプルセグメントとしてサポートされていません。"]}]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_14-0-31.0715052573e26606aa58ae2ec8016dac90eb8b1cd0cb70d6fa6a09f8d02db5ef.cf3845cb.png","alt":""},"children":[]}]},{"$$mdtype":"Tag","name":"ol","attributes":{"start":10},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["スコアリングターゲットを選択します。"," ","これらのプロファイルは、予測の精度をスコアリングするために使用されます。スコアリングターゲットは、行動を予測しようとしているプロファイルのグループです。セグメントまたはペアレントセグメント内のすべてのプロファイルにすることができます。"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["予測しようとしている特性に適合するデータのポジティブサンプルを選択します。"," ","トレーニング母集団とスコアリングターゲットフィールドに選択したデータセットは、ポジティブサンプルフィールドで使用可能な値のリストから除外されます。"]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Next"]},"を選択します。"," ",{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_16-16-12.d91780364d13ba5371406afa352c3d00ef0ee62eddc4bdce11b5ed56273103d3.cf3845cb.png","alt":""},"children":[]}]},{"$$mdtype":"Tag","name":"li","attributes":{},"children":["オプションで、Use suggested featuresを選択します。"," ","予測スコアリングはFeature Guess機能を提供します。Treasure Dataは、アトリビュートから派生した関連性の高いフィーチャー(予測因子)を提案します。"]}]},{"$$mdtype":"Tag","name":"Admonition","attributes":{"type":"info"},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["Feature Guess機能は階層的グルーピングをサポートしていません。Feature Guessはグループアトリビュートを提案しません。"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-14_16-26-0.5d064ce9f2e31af7e2db67f783198573d1be4c2ad4bdbf995f8ac847083a8c06.cf3845cb.png","alt":""},"children":[]}]},{"$$mdtype":"Tag","name":"ol","attributes":{"start":14},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["オプションで、予測を許可する代わりに、以下を定義できます:"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["カテゴリカルフィーチャー"]}," ","値が離散カテゴリに属するアトリビュートまたはグループアトリビュートに使用します。例: ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["_state_"]},"でCA、NY、MAなどの値を持つもの。カテゴリカルアトリビュートは、州や性別のような非順序(名義)、または高、中、低温度のような順序(順序)にすることができます。たとえば、「color」というフィーチャーは、「purple」、「yellow」、「blue」の値を取る場合があります。"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["カテゴリカル配列フィーチャー"]}," ","アトリビュートが",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["interest_words"]},"のようなカテゴリ値の配列を格納する場合に使用します。"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["定量的フィーチャー"]}," ",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["price"]},"や",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["frequency"]},"など、数値を含むアトリビュートまたはグループアトリビュートに使用します。"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":["各フィーチャーフィールドは、アトリビュートのドロップダウンリストを提供します。通常のアトリビュートは上部に表示され、グループアトリビュートは",{"$$mdtype":"Tag","name":"code","attributes":{},"children":["_ [Group]_"]},"プレフィックスを付けて下部に表示されます。"]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/predmodelgroupattrib.d0383233911c175292da04debf1c64d68555eeca1d3698a7eee5e276b32b4ed2.cf3845cb.png","alt":""},"children":[]}]},{"$$mdtype":"Tag","name":"ol","attributes":{"start":15},"children":[{"$$mdtype":"Tag","name":"li","attributes":{},"children":["Save and trainまたは",{"$$mdtype":"Tag","name":"strong","attributes":{},"children":["Save"]},"を選択します。"]}]},{"$$mdtype":"Tag","name":"p","attributes":{},"children":[{"$$mdtype":"Tag","name":"img","attributes":{"src":"/assets/image2021-6-15_10-33-19.bfcf09166c94f6a86b584155a17c5c13756fbfeaabde98d86be774b74cf56c09.cf3845cb.png","alt":""},"children":[]}]},{"$$mdtype":"Tag","name":"Admonition","attributes":{"type":"info"},"children":[{"$$mdtype":"Tag","name":"p","attributes":{},"children":["トレーニング母集団、スコアリングターゲット、またはポジティブサンプルが、フル権限または表示権限のないフォルダ内のセグメントを参照している場合、エラーメッセージが表示されます。"]}]}]},"headings":[{"value":"予測モデルの作成","id":"予測モデルの作成","depth":1},{"value":"予測モデルの定義","id":"予測モデルの定義","depth":1}],"frontmatter":{"seo":{"title":"予測モデルの作成","description":"Audience Studioで予測モデルを作成する手順を解説。機械学習を活用し、セグメントのターゲティングを最適化する方法を詳しく説明します。"}},"lastModified":"2026-06-17T07:22:53.000Z","pagePropGetterError":{"message":"","name":""}},"slug":"/ja/products/customer-data-platform/audience-studio/predictivemodel/create-a-predictive-model-1","userData":{"isAuthenticated":false,"teams":["anonymous"]},"isPublic":true}