~/projects/fintech-invoice2022ReactJavaPython
AI-Powered FinTech B2B Invoice Management
Predicting payment delays with ML
fintech-invoice.proj
Role
Full Stack Developer
Timeline
4 months
Year
2022
Type
Project
// Key Results
89%
Prediction Accuracy
10K+
Invoices Processed
<200ms
Response Time
01 // The Problem
What was broken
B2B finance teams spend countless hours manually triaging invoices to prioritize collection efforts. There was no data-driven way to know which customers would pay late.
02 // The Approach
How I thought about it
Combined a React frontend and Java backend for invoice CRUD operations with a Python ML service that scores each invoice's likelihood of on-time payment using historical features.
03 // The Solution
What I built
A unified dashboard where ops teams can filter invoices by risk score, drill into predicted payment dates, and export reports — all backed by a scalable PostgreSQL schema.
04 // The Impact
Outcomes & learnings
Reduced manual invoice-triage time by an estimated 60% in simulated runs and surfaced high-risk accounts two weeks earlier than heuristics.
// Tech Stack
ReactJava ServletsJDBCPythonscikit-learnPostgreSQL