Koustubh Sharma — studio portrait

Koustubh Sharma

I build risk infrastructure that scales.

Credit policy, loss forecasting & fair lending across a $277.5M, five-brand lending portfolio — plus published research on how AI is changing financial risk.

  • IEEE · ACM · Springer — 40+ citations
  • UC Irvine · MS Business Analytics
  • Journal peer reviewer & judge
  • Featured in Free Press Journal · Republic World

About

I sit at the intersection of credit policy, loss forecasting, and operational intelligence in fintech lending. At National Funding / FairSquare I lead credit-risk analytics across a $277.5M portfolio spanning five brands — National Funding, QuickBridge, SmallBusinessLoans, NFXprs, and Finova Capital.

The thread through everything I do: finding the number everyone else missed. A $1M-per-month write-off reconciliation gap — now fixed company-wide. A syndication expansion led under incomplete data with 3-scenario stress analysis, finishing 59.7% above target. In 2025, net charge-offs came in $15.1M below forecast (−29.6%) on the book I instrument.

My toolkit is the full credit-risk stack — PD/LGD/EAD modeling, vintage and roll-rate analysis, risk-based pricing, line management, and fair-lending compliance (ECOA/FCRA/TILA) — built on Python, SQL, Snowflake, and Tableau.

Outside the day job I research how AI is rewiring financial risk — published in IEEE, ACM, and Springer with 40+ citations, featured in the Free Press Journal, quoted in Republic World and NDTV, and currently writing Risk at Machine Speed, a book on automated decision systems in credit-risk operations.

Experience

  1. Business Intelligence & Risk Analyst · National Funding / FairSquare

    Oct 2024 — Present
    • Lead credit-risk analytics and BI infrastructure across a $277.5M portfolio spanning 5 lending brands — National Funding, QuickBridge, SmallBusinessLoans, NFXprs, and Finova Capital.
    • 2025 performance vs. forecast: gross charge-offs $10.8M favorable (−16.6%), net charge-offs $15.1M favorable (−29.6%), recoveries $4.3M above plan (+30.3%).
    • Discovered and resolved a $1M+/month write-off reconciliation gap through a systematic recon protocol — adopted as the company-wide standard.
    • Led syndication portfolio expansion under incomplete data using 3-scenario stress analysis — finished +59.7% above target; tracked $698.1M in 2025 originations against forecast.
    • Drove risk-vs-sales alignment through partial policy tightening plus a 90-day review framework — stabilized delinquency without killing volume.
    • Built the unified risk-surveillance system from scratch (Snowflake + Tableau) and trained 12 analysts on it; automated reporting saves 20+ hrs/month and cut manual reconciliation 30%.
    • PD / LGD / EAD
    • Vintage & roll-rate
    • Credit policy
    • Snowflake
    • Tableau
    • Python
  2. Risk Analyst · National Funding

    Jun 2024 — Oct 2024
    • Eliminated 30 hrs/week of manual reporting by moving the team from spreadsheets to SQL/Python → Tableau pipelines — doubled refresh frequency, cut investigation time 20%.
    • Stood up Domo as the team's reporting foundation from scratch; trained 12 analysts and managers. The infrastructure is still in active use.
    • Domo
    • SQL
    • Python
    • Tableau
  3. Student Analyst, Economic Research & Forecasting · Pacific Life

    Jan 2024 — Jun 2024
    • Built 4-quarter macro forecasting models (ARIMA, LSTM, Random Forest, Prophet) on Bloomberg Terminal data; ARIMA won on out-of-sample accuracy. Delivered an interactive Streamlit forecasting dashboard and presented to senior research leadership.
    • ARIMA
    • LSTM
    • Streamlit
    • Bloomberg Terminal
  4. Teaching Assistant (UC Irvine) · Digital & IT Intern (Wellness Forever) · Technology Consultant (D-Sys) · Earlier

    2021 — 2024
    • TA for MGMT-90 at UCI's Merage School; at Wellness Forever, analyzed 90,000+ SKUs to build the impulse category (+25% sales) and cut partner-onboarding turnaround 50% through workflow digitization.
    View full resume

    Risk Lab

    Credit-Risk Toolkit

    Live · no charting library

    Three models from my day job, live in your browser. Drag the assumptions and watch the portfolio respond — the same math behind loss forecasting, delinquency surveillance, and pricing on a $277.5M book.

    Vasicek single-factor model — the Basel II framework behind bank capital rules. Expected loss, 99.9% VaR, and the capital buffer between them.

    Expected loss
    99.9% VaR
    Capital buffer

    Built from scratch with no charting library — Vasicek/Basel II capital math, delinquency roll-rate mechanics, and APR construction, straight from the day job.

    The Book

    Forthcoming · 2026

    Risk at Machine Speed

    AI-Augmented Credit Risk Analytics for Lending Professionals

    "The institutions that answered in hours were not smarter. They were better organised. They had built the plumbing before they needed it — which meant they could ask the question before anyone told them to. This book is a guide to building that plumbing."— from the Prologue: March 10, 2023, 6:47 a.m. The morning SVB died.

    Twenty chapters across five parts — from the crises that break portfolios (SVB, tariffs, COVID concentration, the quiet disasters that never make the front page) to what AI tools actually do in a risk war room, where they fail in a regulated environment, and a 90-day build plan for the infrastructure.

    • CH 01

      The Day SVB Died

      What supervision missed, what the data didn't — and the counterparty bank monitor that answers in hours, not days.

    • CH 08

      The 2008 Ghost

      What AI would have found in the mortgage data — re-running the crisis with modern tooling.

    • CH 09

      Ukraine, Wheat, and the Bakery Chain That Ran Out of Margin

      How a war 6,000 miles away compresses the margins of a borrower on Main Street.

    • CH 14

      The Automation Trap

      Knight Capital lost $440M in 45 minutes. What it teaches about putting machines in the decision loop.

    • CH 19

      The 30/60/90-Day War Room Build

      A working plan for standing up AI-augmented risk infrastructure in one quarter.

    • CH 20

      The Next Crisis Is Already in Your Data

      The signals sitting in your portfolio right now — and the plumbing needed to hear them.

    Grounded in named, sourced case studies — SVB, Knight Capital, the 2008 mortgage data, Ukraine's wheat shock, crypto winter — with working SQL and Python builds for each monitor.

    Research & Media

    • 40+ citations

      Peer-reviewed research — IEEE, ACM & Springer

      Publications on predictive analytics for financial risk, AI-driven credit decisioning, comparative BI & data-analytics methods, and online transaction risk factors.

      Google Scholar profile ↗
    • Industry white paper · in progress

      Migrate the Mess, or Mess Up the Migration

      What the AI era demands from your semantic layer. AI agents now consume BI metrics built for human eyes — and a migration is the once-a-decade window to fix that. Centerpiece: a lending case study where three versions of “Delinquency Rate %” silently disagreed in executive reporting for over a year, and the five properties (canonical definitions, explicit grain, logic separation, rich metadata, governed ownership) that make a metric layer AI-ready. Features practitioner interviews across Domo, Tableau, Looker, Power BI, and Qlik.

    • Free Press Journal · Apr 2026

      The Analyst Building Credit Risk Infrastructure for America's Small Business Lenders

      Profile on my work building the credit-risk systems behind $275M+ in SMB lending across five brands — and the forthcoming book.

      Read the profile ↗
    • Republic World · Mar 2026

      War-risk premiums and global oil shipping costs

      Quoted as a risk expert on war-risk insurance mechanics during the West Asia conflict — premium escalation from 0.25% to 1% of hull value and its knock-on effect on energy prices.

      Read the article ↗
    • NDTV · Expert commentary

      GST collections, MSME challenges & India's digital tax infrastructure

      Quoted on tax-reform challenges facing MSMEs — GSTN digital infrastructure, adoption hurdles, and input-tax-credit mechanics.

      Read the article ↗
    • International financial services

      Invited industry training — Ferrum Capital

      Invited to deliver training on credit-risk analytics based on published research.

    Recognition

    • Industry Advisory Board — Southeastern Louisiana University

      Incoming board member, advising on analytics and industry alignment; first board term begins December 2026.

    • Journal peer reviewer — Library Hi Tech (Emerald Publishing)

      Invited reviewer for an established, indexed, peer-reviewed journal — evaluating other researchers' work in information systems and analytics.

    • Conference & competition judging

      Reviewer, ICAIS 2026 (International Conference on Artificial Intelligence Systems); invited judge, TECHNEX 2026, IIT (BHU) Varanasi — selected by invitation from practitioners with demonstrated expertise; judge, NMIMS University national hackathon.

    • Education

      MS Business Analytics — UC Irvine, Merage School of Business. MBA Technology Management & BS Information Technology (Hons.) — NMIMS University, Mumbai.

    • Certifications & compliance

      CSM®, Six Sigma Green Belt, Tableau Desktop Specialist (TDS-C01), IBM Data Science. Fair-lending compliance: ECOA, FCRA, TILA.

    Let's talk about risk, data — or a role.

    I'm always open to conversations about risk analytics, AI governance, and BI leadership roles in financial services.

    koustubh@koustubhsharma.com