Credit Risk & Expected Credit Loss (ECL)

Jul 25, 2026 · 1 min read
projects

Jul 2026

  • Built a Basel-style expected credit loss engine which converts an algorithmic lending model’s output into calibrated PD and combines it with LGD and EAD to produce loan-level ECL.
  • Implemented IFRS-9 three-stage impairment logic and ran LGD sensitivity analysis to test how provisioning shifts under alternative recovery assumptions.
  • Analysed risk-grade deciles and quantified how sharply expected loss concentrates in a small share of the book, which drives a disproportionate share of provisions.
Quantitative Finance Credit Risk IFRS-9 Basel
Porush Yadav
Authors
Porush Yadav

Hi! I am Porush Yadav. I have graduated from IIT Kanpur with a BS-MS Dual Degree in Mathematics and Scientific Computing. I have Worked at Axis Bank on an image recognition system that leverages neural networks to automate document classification and enhance data extraction. Before that, I interned at Samsung R&D Institute India, eJET systems, and EZ Technologies, where I worked on machine learning applications in signal data compression, recommendation systems, classification systems, and image recognition.

I look forward to leveraging AI and ML expertise to develop impactful solutions that can solve real-life problems.