広告配信サーバーと広告配信比率最適化問題

Transcript

1. 1.

   ޿ࠂ഑৴αʔόʔͱ
   ޿ࠂ഑৴ൺ཰࠷దԽ໰୊
   ϝσΟΞϓϩμΫτ։ൃ෦
   ,FOKV
   8BHBUTVNB
   

2. 2.

   8IP Kenju Wagatsuma (github.com/kenju)
 • ϝσΟΞϓϩμΫτ։ൃ෦ • αʔόʔαΠυΤϯδχΞ • ޷͖ͳ΋ͷɿRuby,

   ίʔώʔ, ϩδΧϧΫοΩϯά • ݏ͍ͳ΋ͷɿ1ϲ݄લʹॻ͍ͨࣗ෼ͷίʔυ
3. 3.

   ϝσΟΞϓϩμΫτ։ൃ෦ ୲౰αʔϏεɿ ޿ࠂ഑৴, storeTV, cookpadTV, OEM, ͦͷଞଟ਺ ࢀߟɿ ։ൃऀϒϩάʰΫοΫύουͷ޿ࠂΤϯδχΞ͸ԿΛ ΍͍ͬͯΔͷ͔ʱ

4. 4.

   ຊ೔࿩͍ͨ͜͠ͱɻ ϝσΟΞϓϩμΫτ։ൃ෦Ͱ ͲΜͳϓϩδΣΫτΛ΍͍ͬͯΔͷ͔ʁ

5. 5.

   νʔϜʹೖͬͯϲ݄ޙʹऔΓ૊ΜͩϓϩδΣΫτ ΫοΫύουͷ޿ࠂ഑৴αʔόʔʹ͓͚Δ ޿ࠂ഑৴ൺ཰ͷࣗಈ࠷దԽϓϩδΣΫτɻ

6. 6.

   ݫ͍͠εέδϡʔϧ • ϝσΟΞϓϩμΫτ։ൃ෦δϣΠϯ - 10݄த० • ͓खฒΈഈݟϓϩδΣΫτ - ~11݄த० •

   ഑৴࠷దԽτϥΠΞϧ - 12/4(݄) 10:00 - 12/11(݄) 10:00 ???
7. 7.

   ղܾ͍ͨ͠՝୊ • ೔ʑͷखӡ༻ʹΑΔνϡʔχϯά͕ඞཁ - => ౔೔࡞ۀ͕ൃੜ • ӡ༻ऀͷܦݧͱצʹཔͬͨνϡʔχϯά - =>

   ҟಈ࣌΍ಋೖ࣌ͷίετ͕ߴա͗໰୊ • ࠷దͳࡏݿൺ཰ΛࣗಈͰௐ੔Ͱ͖ͳ͍ - => ޿ࠂ঎඼ܝग़ͷػձଛࣦ
8. 8.

   Ͳ͏ղܾ͢Δ͔ • ࡏݿׂ౰ྔͱ࣮੷஋͔Β࠷దͳ഑৴ൺ཰ͷิ ਖ਼Λߦ͏ - ΠϯϓϨογϣϯϕʔε͔ΒΫϦοΫ਺ϕʔεͷ഑৴΁ - ΫϦοΫ཰༧ଌΛར༻ͨ͠഑෼ൺ཰ͷࣗಈ࠷దԽ - ϦΞϧλΠϜूܭσʔλΛ׆༻ͨ͠ΞʔΩςΫνϟ

   ‣ Lambda Architecture ʹ͓͚Δ Speed Layer
9. 9.

   l4QFFE
   -BZFSz
   PO
   "84 • Kinesis, DynamoDB, Lambda Λ׆༻ͨ͠ Speed Layer (from Lambda

   Architecture) • طଘͷετϦʔϜʹɺΫ ϦοΫ཰ܭࢉϨΠϠʔΛ ௥Ճ͚ͨͩ͠ = ઌਓͷݞ ʹ৐Δ
10. 10.

    ৄ͍͠࿩͸ͪ͜Β ࢀߟɿ ʰCookpad Tech Kitchen #9 ʙ1ߦͷϩάͷ޲͜͏ ଆʙ Λ։࠵͠·ͨ͠ʂʱ

11. 11.

    ΫϦοΫ཰༧ଌ͸೉͍͠ʂʂʂ • ޯ഑ϒʔεςΟϯάܾఆ໦ʢGBDTʣΛ༻͍ͨ޿ࠂ͝ͱͷΫϦοΫ཰༧ଌ - Facebook https://code.facebook.com/posts/975025089299409/evaluating-boosted-decision-trees-for-billions-of-users - SmartNews https://speakerdeck.com/komiya_atsushi/gbdt-niyorukuritukulu-yu-ce-wogao-su-hua-sitai-number-oresikanaito-vol-dot-4 •

    ଟ࿹όϯσΟοτ໰୊ͷҰछͰ͋ΔMortal Multi-Armed BanditsͷԠ༻ - Voyage Group http://techlog.voyagegroup.com/entry/2015/04/03/114547ɹ • Neural Networkͷ૯߹֨ಆٕʢ͕͢͞Googleʣ - Google http://www.eecs.tufts.edu/~dsculley/papers/ad-click-prediction.pdfɹ • ৴པͱ࣮੷ͷϩδεςΟοΫճؼʢୠܻ͕͠ԯϨϕϧʣ - Criteo http://olivier.chapelle.cc/pub/ngdstone.pdfɹ
12. 12.

    ؒʹ߹Θͳ͍ʂ • τϥΠΞϧ͸ͳΜͱͯ͠΋೥಺ʹ࣮ࢪ͍ͨ͠ - վળͷαΠΫϧΛճͨ͢Ί • QCDͰݴ͏ͳΒɺDelivery, QualityΛ༏ઌ - ͳΜͱͯ͠΋ؒʹ߹Θ͍ͤͨʂ

    • ࠷ॳ͔Β׬ᘳͳਫ਼౓༧ଌ͸·ͣෆՄೳ - ػցֶशͰղܾ͠ͳͯ͘΋Α͍͔·ͣߟ͑Δ - ࢀߟɿʰ࢓ࣄͰ͸͡ΊΔػցֶशʱ
13. 13.

    Ҡಈฏۉ΋Ԟ͕ਂ͍ • SMA (Simple Moving Average) = ௚ۙ N ݸͷॏΈ෇͚ͷͳ͍୯७ͳฏۉ

    • WMA (Weighted Moving Average) = ΑΓ࠷ۙͷσʔλʹॏΈ෇͚ • EWMA (Exponentially Weighted Moving Average) = ࢦ਺ؔ਺తʹॏΈ෇͚ • MMA (Modified Moving Average) = EWMAͷѥछ ଞʹ΋Triangle MA, Sine Weighted MA, KZ Filtering,...etc ࢀߟɿhttps://en.wikipedia.org/wiki/Moving_average#Simple_moving_averag
14. 14.

    աڈϩάΛݩʹΞϧΰϦζϜͷਫ਼౓Λ෼ੳ • Jupyter Notebook / Python - ࢀߟɿ։ൃऀϒϩάʰRailsΤϯ δχΞʹ໾ཱͭJupyter Notebook

    ͱiRubyʱ • ൺֱͨ͠ΞϧΰϦζϜ - Total Average - Cumulative Average - Simple Moving Average (3 Hours) - Simple Moving Average (6 Hours)
15. 15.

    τϥΠΞϧ݁Ռ • ิਖ਼ͷϩδοΫʹ՝ ୊͕ݟ͔ͭͬͨ΋΋ ͷɺτϥΠΞϧͱ͠ ͯ͸੒ޭ

16. 16.

    ୹ظతνϡʔχϯά • Speed Layer ͷ࠶ઃܭɾຏ͖ࠐΈ - ετϦʔϜॲཧʹԊͬͨσʔλͷྲྀΕ • ෛ࠴ =

    ະୡ෼ ΛՃຯͨ͠ϩδοΫ - ୈҰ࣍τϥΠΞϧΛ΍͍ͬͯͳ͔ͬͨΒݟ͑ͳ͔ͬͨ՝୊ • ҠಈฏۉΞϧΰϦζϜͷվળ - Batch LayerͰΦϑϥΠϯͰܭࢉ&࠷΋ਫ਼౓͕ྑ͍΋ͷΛબ୒ - Gem࡞ͬͨ https://github.com/kenju/moving_avg-ruby
17. 17.

    த௕ظͰ΍͍͖ͬͯ • ΫϦοΫ཰༧ଌਫ਼౓ͷߋͳΔ޲্ˍ৽ن޿ࠂ঎඼։ൃ - ػցֶशϨΠϠʔͷຊ൪ಋೖ • Lambda Architectureͷຏ͖ࠐΈ - ࢀߟɿ։ൃऀϒϩάʰαʔόʔϨεͳόοΫΞοϓγεςϜ

    Λ AWS SAM Λ༻͍ͯγϡοͱߏங͢Δʱ • ޿ࠂ഑৴αʔόʔࣗମͷѹ౗తվળ - ։ൃج൫ͷ؀ڥ੔උ - ύϑΥʔϚϯε࠷దԽɺϨΨγʔίʔυͷվળ
18. 18.

    ຖ೔ͷྉཧΛָ͠Έʹ͢Δ 5IBOL
    ZPV