D2-3-S09_秒間_6_万イベントの大規模リアルタイムデータを活用する機械学習基盤の実現__抜粋版_.pdf

Transcript

1. 牧野 祐己 CTO PLAID
   2019 年 8 月 1日
   D2-3-S09:
   秒間 6 万イベントの大規模
   リアルタイムデータを活用する
   機械学習基盤の実現
   ※本資料は当日登壇資料の一部を抜粋しています。
   

   View Slide

2. 02
   リアルタイムデ
   ータ分析基盤と
   学習基盤
   

   View Slide

3. 牧野 祐己
   Chief Technology Officer
   

   View Slide

4. at GINZA SIX
   

   View Slide

5. Customer Experience Platform
   Real-time Analytics & Action Tool
   karte.io
   

   View Slide

6. どれくらいリアルタイムデータを
   処理しているか？
   65,000
   events
   (rows) / sec
   3 billion
   events per day
   2+ PB
   stored in
   BigQuery
   1 PB
   streaming insert
   per month
   0.x
   sec to real-time
   actions
   60+ PB
   analysis per
   month
   6,000
   slots with flat
   Rate US & JP
   500+
   datasets for
   clients
   

   View Slide

7. データ分析基盤のアーキテクチャ
   Reactive Layer
   Track
   Compute Engine
   Autoscaling
   BigQuery
   Cloud
   Spanner
   Cloud
   Pub/Sub
   Cloud
   Dataflow
   Admin
   Compute Engine
   Autoscaling
   Analyze
   Compute Engine
   Autoscaling
   Cloud
   Bigtable
   65,000
   events / sec
   Redis
   Redis
   Cloud
   Bigtable
   Object
   Storage
   Salesforce Others...
   ELT
   Streaming
   Insert
   Client
   Cloud
   Storage
   1 PB
   streaming insert
   per month
   Import / Export
   

   View Slide

8. データ活用における大事なポイント
   ● とりあえずデータは全部突っ込んでから考える
   ● データをどう使うか、から考える
   ● 活用時はクライアントがコントローラブルであること
   ● とりあえず活用してみて調整していく
   

   View Slide

9. 機械学習基盤で実現するライフサイクル
   1. データ投入と前処理
   2. 学習と検証
   3. モデルのデプロイ
   4. 予測とアクション
   そのサイクルをまわす
   Prepare
   Pre-process
   Ingest
   Train
   Evaluation
   Deploy
   Predict
   

   View Slide

10. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest Train, Evaluation
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    End-User
    End-User
    ML Architecture
    

    View Slide

11. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest
    ML Architecture
    

    View Slide

12. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest Train, Evaluation
    Batch Training
    Job
    Model
    Store
    ML Architecture
    

    View Slide

13. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest Train, Evaluation
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    ML Architecture
    Deploy
    

    View Slide

14. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest Train, Evaluation
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    End-User
    End-User
    ML Architecture
    

    View Slide

15. 03
    GCPによる実現
    と活用事例
    

    View Slide

16. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Prepare, Pre-process, Ingest Train, Evaluation
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    End-User
    End-User
    ML Architecture
    

    View Slide

17. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    BigQuery
    BigQuery
    BigQuery
    AI Platform
    Training
    Cloud
    AutoML
    BigQuery
    ML
    BigQuery
    Cloud
    Bigtable
    AI Platform
    Prediction
    Cloud
    AutoML
    API
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    BigQuery
    ELT
    Periodically Update
    Daily/Weekly /Monthly
    

    View Slide

18. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    Periodically Update
    Daily/Weekly /Monthly
    

    View Slide

19. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    Periodically Update
    Daily/Weekly /Monthly
    BigQuery
    BigQuery
    BigQuery
    BigQuery
    ELT
    

    View Slide

20. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    Periodically Update
    Daily/Weekly /Monthly
    BigQuery
    BigQuery
    BigQuery
    BigQuery
    ELT
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    

    View Slide

21. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    Periodically Update
    Daily/Weekly /Monthly
    BigQuery
    BigQuery
    BigQuery
    BigQuery
    ELT
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    AI Platform
    Training
    Cloud
    AutoML
    BigQuery
    ML
    

    View Slide

22. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    Periodically Update
    Daily/Weekly /Monthly
    BigQuery
    BigQuery
    BigQuery
    BigQuery
    ELT
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    AI Platform
    Training
    Cloud
    AutoML
    BigQuery
    ML
    BigQuery
    Cloud
    Bigtable
    

    View Slide

23. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Batch Predict
    Job
    Real-time
    Predict Service
    Predict
    Key -
    Value
    Store
    Prediction
    Data
    Deploy
    Predict
    End-User
    End-User
    Predict
    GCP で実現
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    BigQuery
    BigQuery
    BigQuery
    AI Platform
    Training
    Cloud
    AutoML
    BigQuery
    ML
    BigQuery
    Cloud
    Bigtable
    AI Platform
    Prediction
    Cloud
    AutoML
    API
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    BigQuery
    ELT
    Periodically Update
    Daily/Weekly /Monthly
    

    View Slide

24. BigQueryを中心のデータストア
    とする機械学習基盤 Before
    BigQuery
    Cloud
    Dataflow
    BigQuery
    Cloud
    Bigtable
    Cloud
    Spanner
    AWS S3
    Cloud
    Storage
    SFTP
    Treasure Data
    Salesforce Cloud
    Spreadsheet
    External Data
    ELT
    Import
    Export
    BigQuery
    

    View Slide

25. BigQueryを中心のデータストア
    とする機械学習基盤 After
    BigQuery
    Cloud
    Dataflow
    BigQuery
    Cloud
    Bigtable
    Cloud
    Spanner
    AWS S3
    Cloud
    Storage
    SFTP
    Treasure Data
    Salesforce Cloud
    Spreadsheet
    External Data
    ELT
    Import
    Export
    BigQuery
    AI Platform
    Training
    Cloud
    AutoML
    BigQuery
    ML
    ML
    Predict
    

    View Slide

26. データ活用における大事なポイント
    ● とりあえずデータは全部突っ込んでから考える
    ● データをどう使うか、から考える
    ● 活用時はクライアントがコントローラブルであること
    ● とりあえず活用してみて調整していく
    

    View Slide

27. 事例 1: BigQuery ML k-means で
    ユーザーをクラスタリング
    サイトのユーザーを RFM パターンで
    クラスタリングする
    Recency: 最後に”購入”してからの時間
    Frequency: ”購入”の頻度
    Monetary Value: ”購入”の価値の大きさ
    CREATE OR REPLACE MODEL
    `cloud_next_session.rfm_cluster`
    OPTIONS
    (model_type='kmeans',
    num_clusters=4,
    standardize_features = TRUE) AS
    SELECT
    *
    FROM (
    SELECT
    SUM(revenue) monetary,
    COUNT(*) frequency,
    MAX(_date) recency
    FROM
    `karte.events`
    WHERE
    event_name = 'buy'
    GROUP BY
    keys.visitor_id )
    

    View Slide

28. ユーザーをクラスタリングして
    セグメンテーションに利用
    

    View Slide

29. BI ツールで可視化
    

    View Slide

30. 事例 3: AI Platform で
    リアルタイムに購入予測
    https://aaa.com/
    category/items
    https://aaa.com/top
    https://aaa.com/
    category/item/X
    XXXXXX
    CNN
    CNN
    CNN
    Embedding
    feature
    vector
    CNN
    True /
    False
    TensorFlow
    

    View Slide

31. 事例 3: AI Platform で
    リアルタイムに購入予測
    BigQuery
    Cloud
    Dataflow
    Cloud
    Storage
    TensorFlow
    AI Platform
    Training
    Preprocess Train Deploy
    Ingest
    Realtime
    API
    

    View Slide

32. View Slide

33. Real-time
    Offline
    Analyze
    Key -
    Value
    Store
    Data
    Lake
    Ingest Prep
    Training
    Data
    Store
    Feature
    Store
    Ingest Train & Eval
    Batch Training
    Job
    Model
    Store
    Real-time
    Predict Service
    Predict
    Deploy
    Predict
    End-User
    Cloud
    Pub/Sub
    Cloud
    Bigtable
    BigQuery
    BigQuery
    BigQuery
    AI Platform
    Training
    Cloud
    AutoML
    AI Platform
    Prediction
    Cloud
    AutoML
    API
    Cloud
    Dataflow
    Cloud
    Dataproc
    Cloud
    Dataprep
    BigQuery
    ELT
    Feature
    Feature
    Real-time Pattern
    

    View Slide

34. リアルタイム予測か、バッチ予測か？
    リアルタイム予測
    Pros
    - モデルの更新頻度が高い
    - 予測結果変動が大きい場合
    - 必要な場合だけ計算
    Cons
    - 使える Feature が限定的
    バッチ予測
    Pros
    - 複雑な Feature が利用できる
    - アーキテクチャがシンプル
    - 予測結果が確認できる
    Cons
    - モデルの更新頻度が低い
    - ありうる対象すべて計算しておく
    

    View Slide

35. 04
    まとめ
    

    View Slide

36. まとめ
    リアルタイムデータ分
    析基盤を元に機械学習
    基盤を構築
    GCP のさまざまなデ
    ータ、機械学習サービ
    スを利用してシンプル
    に実現
    実際に活用している
    リアルタイム、バッチ
    の3事例を紹介
    

    View Slide

37. Thank you
    

    View Slide