Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Intelligent Customer Support for the Masses: How Nubank does it

Fuad Saud
September 21, 2018

Intelligent Customer Support for the Masses: How Nubank does it

Fuad Saud

September 21, 2018
Tweet

More Decks by Fuad Saud

Other Decks in Technology

Transcript

  1. THE PROMINENT BITS • Fintech • Credit Card • Rewards

    • NuConta (Payments Account) ◦ More than R$9 billion in transactions • More than 4 million customers THE PROMINENT BITS
  2. COMPLEX DOMAIN • Failure in third-party financial systems • Customers

    need to negotiate their debt. • People get scammed/frauded
  3. CUSTOMER SUPPORT FIGURES • Xpeers represent 60% of Nubank’s headcount

    (24/7 team) • 13k emails/day • 20k chats/day • 7k phone calls/day
  4. SQUADS MODEL OPS TEAMS • Bills • Customer Acquisition •

    Chargebacks • Collections • Fraud • Limits • Logistics • Payments • NuConta • Rewards
  5. • Human made • Let the users correct it when

    necessary • Good to prototype the routing system • Capture the performance • Use as benchmark RULE BASED
  6. A CLIENT THAT HAS A CARD IN ROUTE SHOULD GO

    DIRECTLY TO THE LOGISTICS QUEUE
  7. • Learns to route • Improves with time • Still

    uses rules when necessary MACHINE LEARNING • Human made • Let the users correct it when necessary • Good to prototype the routing system • Capture the performance • Use as benchmark RULE BASED
  8. “You can ask for a credit limit increase using the

    app, it’s easy: on the home screen, look for the 'Limit Settings’ shortcut. Then tap 'Request new maximum credit limit amount’ and you can enter the amount needed. Then tap 'Request' and select a reason. You’ll get feedback about the request in realtime and further details will arrive at you email inbox, ok?”
  9. Hi, I’d like to get a nubank card... I lost

    my password!!!!... ... order-card recover-password ...
  10. RULES ARE A WAY TO JUMPSTART SUCH PROJECTS AND CREATE

    A MODELLING CYCLE. DON’T BE AFRAID OF THEM.
  11. FUTURE WORK • ML everywhere: reply chats, FAQ, dimensioning •

    Rethink the self-help experience to make it more interesting and effective