AVP/VP - Data Science - BFSI

- This position of Data Science will play a key role in exploring alternative datasets and machine learning algorithms for feature engineering and risk predictions that will signal credit strategies.

- The key objective of the newly created data science vertical in the credit function will be to explore new and emerging areas of data, algorithms, and computing to give a competitive edge to our credit decision making.

- The individual should be able to think dynamically, work independently and provide thought leadership in the design and development of the framework for feature engineering and empirical evaluation of alternate algorithms for risk prediction.

- The role will work closely with senior leadership teams to review the insights and influence the adoption of alternative methods of credit decision making, within the guardrails of regulatory requirements.

- This position is remote, where you have the option to work from home. On occasion we may request for you to commute to our nearest office for in person engagement activities such as team meetings, training and culture events. To ensure the safety of our colleagues and communities, we require employees who come together in-person to be fully vaccinated. We're proud to offer you choice and flexibility.

Essential Functions / Responsibilities:

- Analyzing large and multi-dimensional alternative datasets and synthesizing insights into actionable signals for credit models and strategies

- Feature engineering on both structured and unstructured datasets, exploring traditional and new methodologies in feature engineering

- Creating reproducible assets to generate feature stores for multiple use cases using adaptive Artificial intelligence

- Empirical evaluation of alternative data and algorithms (machine learning) in predicting risk with a thorough understanding of the trade-offs between predictive power, fairness, explainability and accountability of the features and the models/ strategies

- Support the identification of best practices in feature engineering and usage, credit models using machine learning algorithms in a cross functional space for efficient credit decisioning

- Liaising with senior leadership to review insights and incremental value proposition upon adoption of the new methodologies in credit decisioning.

Qualifications / Requirements:

- Bachelor's degree in any quantitative discipline - such as engineering, computer science, economics, statistics, operational research, or mathematics with minimum 5+ years of experience in credit analytics in financial services domain, or in lieu of a degree 7+ years of relevant work experience

- Fluent in SAS and SQL, Excel, and visualization tools such as Tableau and QlikView. Proven ability to program in big data technologies.

- Hands on experience in Python or PySpark with statistics and data science libraries

- Domain expertise in financial services - such as banking, fintech, credit bureaus, NBFC's, management consulting in financial services. US market, financial services analytics experience will be preferred

- Comprehensive understanding of data dimensions used in credit decision making, credit strategies and credit modeling methodologies across the lifecycle of credit

- Strong project management skills

- Exceptional communication skills, both written and verbal, to influence cross functional teams and senior stakeholders

- Prior experience of exploring feature engineering techniques using machine learning algorithms will be preferred

- Prior experience of working with the US credit bureau raw data will be highly valued