Upwork home
Sign up
Project Catalog
DesignDesign
Video & AudioVideo & Audio
Development & ITDevelopment & IT
MarketingMarketing
Writing & TranslationWriting & Translation
MoreMore

You will get End-to-End Credit Risk Modeling (PD, LGD, EAD)

Shubham M.Status: Offline
Shubham M. Shubham M.
Preview image

Let a pro handle the details

Buy Machine Learning services from Shubham, priced and ready to go.
Shubham M.Status: Offline
Shubham M. Shubham M.
Preview image

Let a pro handle the details

Buy Machine Learning services from Shubham, priced and ready to go.

Project details

The project will mainly focus on addressing the business requirement rather than delivering true, false, or default/non-default. I will provide an ordinal classifier with P1, P2, P3, and P4, where P1 is the best borrower, and P4 is the worst; you can then decide, based on your business needs, whether to be conservative or aggressive.
Machine Learning Tools
Microsoft Excel, NumPy, pandas, Python, Python Scikit-Learn, scikit-learn, SciPy, XGBoost

What's included $700

These options are included with the project scope.

$700
  • Delivery Time 10 days
  • Number of Revisions 3
    • Model Validation/Testing
    • Model Documentation
    • Data Source Connectivity
    • Source Code
Shubham M.Status: Offline

About Shubham

Shubham M.Status: Offline
Credit Risk Modeller
Jaipur, India - 2:06 am local time
Credit Risk Analyst with an MSc in Banking and International Finance from Bayes Business School and CFA Level II completed. My work focuses on credit risk modelling, financial analysis, and data-driven risk assessment within banking and financial services.
I have built end-to-end credit risk models covering Probability of Default (PD), Loss Given Default (LGD), and Exposure at Default (EAD) on datasets exceeding 460,000 observations using Python and SQL. The modelling process included data preparation, WOE and IV analysis, logistic regression, and validation using ROC AUC, Gini coefficient, and KS statistics. The models were developed with reference to Basel III concepts and IFRS 9 impairment principles.
In parallel, I developed financial simulation models using Black-Scholes and Binomial Tree methods to analyse option pricing and volatility using Nifty50 market data. These projects strengthened my quantitative modelling and financial analytics capabilities.
Previously, I worked as a Credit Risk Data Analyst at Infospectrum in London, where I built an automated reconciliation model using Advanced Excel across more than 120 entities. This reduced data inconsistencies by 40% and reporting discrepancies by 33%, improving the reliability of financial reporting. I also conducted counterparty risk assessments using over 40 financial ratios covering liquidity and solvency metrics, improving internal risk grading accuracy by 30%.
I also led a team of three analysts to redesign credit review workflows, increasing operational throughput by 50% while maintaining quality standards.
My technical skills include Python (Pandas, NumPy, Scikit learn), SQL, and Advanced Excel, including VBA and macros. I regularly work with large datasets, build statistical models, and translate financial data into structured risk insights.

Steps for completing your project

After purchasing the project, send requirements so Shubham can start the project.

Delivery time starts when Shubham receives requirements from you.

Shubham works on your project following the steps below.

Revisions may occur after the delivery date.

Data Cleaning and Preprocessing.

Review the work, release payment, and leave feedback to Shubham.