Senior Manager-Data Science-Data Scientist

EXL Talent Acquisition Team; Gurugram District; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

EXL Talent Acquisition Team is seeking a data scientist to design and build credit risk scorecards, including application, behavioral, and collections models. The role involves SQL-based data extraction and preprocessing, and developing ML models in Python using pandas and scikit-learn.

You will monitor performance, perform backtesting and recalibration under regulatory standards, and collaborate with business and data teams to translate risk requirements into modeling specifications, while

Qualifications

• Experience building credit risk scorecards.
• Proficiency in Python and ML libraries.
• SQL data extraction and preprocessing.
• Understanding regulatory standards in modeling.
• Strong collaboration with business and data teams.
• Documentation of modeling processes and results.

Responsibilities

• Design and build credit risk scorecards (application, behavioral, and collections) to predict creditworthiness and optimize account management strategies.
• Extract, clean, and preprocess data from various sources using SQL.
• Develop and implement ML models for collections performance and delinquency prediction using Python (pandas, scikit-learn).
• Monitor model performance, conduct backtesting, recalibration, and validation per regulatory standards.
• Collaborate with business and data teams to translate credit risk requirements into modeling specifications.
• Document modeling processes, assumptions, and results for governance and audit.

Skills

SQL

Python

Data prep

ML modeling

Tools

pandas

scikit-learn

Job description

Design and build credit risk scorecards (application, behavioral, and collections scorecards) to predict creditworthiness and optimize account management strategies.

Extract, clean, and preprocess data from various sources using SQL.

Develop and implement machine learning models for collections performance and delinquency prediction using Python (including libraries like pandas, scikit-learn).

Monitor model performance, conduct backtesting, recalibration, and validation adhering to regulatory standards.

Collaborate with business and data teams to translate credit risk requirements into modeling specifications.

Document modeling processes, assumptions, and results for internal governance and audit purposes.