Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives

Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives

社内分析会議での発表資料

67d58b26197110809c99b7ef43f8e0f6?s=128

Takahiro Yoshinaga

June 04, 2019
Tweet

Transcript

  1. - 1 - 1 1 1 1 1 1 -

    1 - 0- - 1 - 1 - - 1 - I 1 :67A . 9 0: 565 / 5 : 17 : 5 : , ( , , ) 25 59: 4 A9: 585
  2.   • Cd a lm ro • lm h

    c lm k • lm C , , t • , , , A n sve • oiC C
  3. • l T • P c G P ( •

    c • ( P ) C G • G ( G i koc P C • ) C ( t C G ( TC • P n A R : C • G ( • G C TV
  4. • C V • R • V • C •

    R • C • ! • C V C
  5.   • + + - + - • -

    - + -
  6. • 6 - + • U 1 AV L G

    G S T R C M
  7. • + 0 +2 - + 20-0 • P T

    L M P E
  8. - - • ( 1 0 1 • E •

    02/1 * ) • - , , , 8 S D MR 8 7
  9.   • V V a t C o VAl

    Al • i a i V i V • e n • a V d ↓
  10. • uD To l A c ME sT r gd

    G • - • - • - h e a be G D AC x C G • n t D + T G G AC P L • t Tik