No. 008 · Catalogue entry
Paints Receivables ML Model
DataAI
Role/Management Intern, Digital and Finance · Apr 2024 to Jun 2024
TypeData · AI
Project entry
_
Moves
01 · Model the Risk
Built an ML model predicting accounts-receivable risk and per-dealer default probability from 2+ years of dealer data across 250+ dealers and ~Rs 20 crore of average monthly receivables.
02 · Validate It
Validated the model at about 93% accuracy.
03 · Design the Framework
Built a risk-based dynamic credit-limit framework segmenting dealers by payment behaviour and credit risk.
04 · Pitch It Up
Presented findings and the framework to senior finance and digital leadership.
Outcome
Projected to cut overdue accounts by roughly 25%, recognized by the CDO, and led to a Pre-Placement Offer.
See on resume ↗Role & scope
Solo intern project: built and validated the model and the credit-limit framework myself, with finance/digital leadership as the decision-makers on rollout.