AI & Data Science in Fintech
Avatar of david-miller david-miller
david-miller
August 24, 2025 at 12:10 pm

What data do we actually need for ML underwriting?

What data do we actually need for ML underwriting?

I’m researching this for a project and would love real-world input. If you’ve built or shipped something here, what did you learn? Context: I’m Mila Reed and I’m evaluating options for our team.

4
4

  • Avatar of Daniel Alcanja

    Daniel Alcanja

    August 24, 2025 at 8:10 pm

    Process tip that prevented a week of rework. Document assumptions so new teammates move faster. Track approval rate, chargebacks, and complaints weekly.

  • Avatar of Filipe Gonçalves

    Filipe Gonçalves

    August 25, 2025 at 11:10 pm

    Counterpoint based on what stuck in reality. Watch hidden dependencies that slow audits. Ignore shiny features until you validate ROI.

  • Avatar of Lace Brunsden

    Lace Brunsden

    August 26, 2025 at 4:10 pm

    Ignore shiny features until you validate ROI. Counterpoint based on what stuck in reality. Bias toward tools the team can actually operate.

  • Avatar of Lace Brunsden

    Lace Brunsden

    August 27, 2025 at 2:10 pm

    Document assumptions so new teammates move faster. Process tip that prevented a week of rework. Set crisp ownership so decisions don’t stall.

Log in to reply.