Mercari Tech Conf 2018 Keynote (Dr. Mok Oh)

92cdcff298e89e2fcd2fb705155c2d4b?s=47 mercari
October 04, 2018

Mercari Tech Conf 2018 Keynote (Dr. Mok Oh)

Mok Oh, PhD
CTO, Mercari US

Mercari JP CTO Suguru Namura, Mercari US CTO Mok Oh, and Merpay Director Keisuke Sogawa will discuss the events that have occurred at their respective companies in the past year. They will also talk about the goals and technical challenges that they plan to tackle in the future.

92cdcff298e89e2fcd2fb705155c2d4b?s=128

mercari

October 04, 2018
Tweet

Transcript

  1. Keynote Dr. Mok Oh CTO, Mercari US

  2. 4 October 2018 Mok Oh, PhD Chief Technology Officer Mercari

    US x Mercari Engine
  3. Mercari Engine x Discovery x Exchange

  4. Data x fML Mercari Engine Discovery x Exchange x

  5. People x Culture Mercari Engine Discovery x Exchange x Innovate

    Automate Data x fML
  6. Discovery x Exchange x Mercari Engine

  7. Discover Shop Want Get Buy Buyer

  8. Want Discover Shop Buy Get Buyer’s Journey

  9. Discover Own List Sell Ship Seller

  10. Own Discover List Sell Ship Want Discover Shop Buy Get

    Seller’s Journey
  11. Own Discover List Sell Ship Want Discover Shop Buy Get

    Discovery Exchange
  12. Discovery x Exchange x

  13. Mercari Engine x Discovery x Exchange

  14. Mercari Engine Discovery x Exchange x Data x fML

  15. Data Mercari Engine

  16. None
  17. None
  18. Seller Buyer Item Item Name Price Category Brand Description Photos

    Date Size Weight … Name Email Balance Followers Following Coupons Badges Items listed Items sold Items bought Likes Social Payment … Name Email Balance Followers Following Coupons Badges Items listed Items sold Items bought Likes Social Payment …
  19. All Items ~100M Unique Product “SKUs” f Item matching Retail

    price Size Weight Category Brand Description Photos URLs …
  20. All Items All Sellers All Buyers f Listing optimization f

    Demand optimization f Pricing optimization f Similar items f Category & brand normalization f Item sellability f Item buyability f Fraud items f Item genome f Supply optimization f Seller cancellation f Top sellers f Similar sellers f Fraud sellers f Seller genome f Top buyers f Similar buyers f Buyer cancellation f Fraud buyers f Buyer genome f Sentiment analysis f CS auto classifier f CS chatbots fML
  21. Data Mercari Engine

  22. Mercari Engine fML

  23. Genome Mercari Engine fML

  24. f

  25. input f ( )

  26. input f ( ) output =

  27. f ( ) output = Item Name Price Category Brand

    Description Photos Date Size Weight …
  28. [ ] n-dimensional vector f ( ) = x1 x2

    x3 … xn Item Name Price Category Brand Description Photos Date Size Weight … Genome
  29. f ( ) = Items

  30. Clustered Items

  31. Clustered Items

  32. laptops smartwatches iPhones apparel clothes Nikes

  33. - f ( ) = f ( ) - f

    ( ) = f ( ) fsimilarity ( , ) = 0.78 fsimilarity ( , ) = 0.12 “If you liked , then you may also like .”
  34. [ ] f ( ) =

  35. flook_alikes ( )= { } “Similar sellers also sold .”

  36. Nike Rae Dunn PINK LuLaRoe Nintendo Funko

  37. Nike

  38. Rae Dunn PINK LuLaRoe Nintendo Funko

  39. Data Science Analysis - Female Buyers Technology Mom Buyer Women’s

    Fashion Women’s Accessories Home Technology Beauty Vintage Mom Buyer Submarkets Identified Women’s Fashion Women’s Accessories Submarkets with highest growth rates, STR, and GMV High Growth Submarket Opportunities:
  40. Data Science Analysis - Male Buyers Submarkets with highest growth

    rates, STR, and GMV Technology Submarkets Identified Technology Home Men’s Fashion Collectibles Women’s Accessories High Growth Submarket Opportunities: Home Collectibles
  41. Mercari Engine Genome fML

  42. Mercari Engine Prediction fML

  43. f ( ) Sale probability within 72 hours = i.e.

    What is it’s Sellability Score?
  44. Month 4 Month 0 Sellability Score 0.0 1.0

  45. Month 4 Month 0 0.0 1.0 ! Sold Sold Sellability

    Score
  46. f( ) Probability of Seller canceling =

  47. Month 4 Month 0 Cancel Score 0.0 1.0

  48. Month 4 Month 0 Cancel Score 0.0 1.0 Cancelled !

    Cancelled
  49. f ( ) Counterfeit? = f ( ) Churn? =

    f ( ) Own this item to list? = f ( ) Buy this item? = …
  50. All Items All Sellers All Buyers fML

  51. Mercari Engine Discovery x Exchange x Data x fML

  52. People x Culture Mercari Engine Discovery x Exchange x Data

    x fML
  53. People x Culture Mercari Engine

  54. US@Tokyo US@Palo Alto US@Portland US@Boston

  55. None
  56. Technology Advisory Board Professor Fredo Durand CSAIL, MIT Professor Wojciech

    Matusik CSAIL, MIT
  57. Design PM iOS Android Web Backend ML Data Eng QA

    Growth Search Conversion Completion Support Foundation Teams Scrum Themes
  58. People x Culture Mercari Engine

  59. People x Culture Mercari Engine Innovate Data x fML

  60. People x Culture Mercari Engine Discovery x Exchange Innovate Automate

    Data x fML
  61. 4 October 2018 Mok Oh, PhD CTO, US Thank You!