AI & Data Science in Fintech
Avatar of liam-yates liam-yates
liam-yates
September 30, 2025 at 8:03 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 Carter Ward and I’m evaluating options for our team.

3
2

  • Avatar of Filipe Gonçalves

    Filipe Gonçalves

    October 2, 2025 at 8:03 am

    Shadow‑run the new stack for a week before go‑live. Quick checklist that saved us time. Push data contracts upstream so APIs don’t drift.

  • Avatar of Marcelo Pantoja

    Marcelo Pantoja

    October 3, 2025 at 7:03 am

    We shipped something similar last quarter; notes below. We cut manual review time by ~30% just by clarifying thresholds. Prioritize measurable lift over theoretical accuracy.

Log in to reply.