Job Requirements:

• Bachelor/master’s degree in CS, IT, or a similar field.
• Should have strong fundamentals in machine learning, general statistics and data science principles.
• Have understanding or previously worked on Credit Risk Modelling and also have knowledge of financial domain, preferably of collections, recoveries and knowledge of various supervised and unsupervised ML techniques.
• Should have hands on experience with some of these methods: Regression, Decision Trees, CART, Random Forest, Boosting, Evolutionary Programming, Neural Networks, Support Vector Machines, Ensemble Methods, Association Rules, Principal Component Analysis, Clustering, Artificial Intelligence, Deep learning, TensorFlow, Keras etc.
• Programming Language: Python/SQL (Must), familiarity with big data concepts will be an added advantage
• Knowledge of complete life cycle of a data science project & solution development, problem statement to the deployment of solution on cloud or on-premises infrastructure. Knowledge of popular cloud ML frameworks like AWS Sage Maker, Google ML studio is desired.
• 3+ years of hands-on experience in data science using techniques including but not limited to regression, classification, NLP etc.
• Previous experience in model deployment, model monitoring, optimization and model interpretability.

• Develop Algorithms/scorecards which are predictive/prescriptive in nature across the lending value chain of portfolio management, collections and recoveries.
• Perform tracking, analysis and provide insights on Portfolio performance as well as operational metrics.
• Work with both traditional and alternate data sources to improve the scorecards and rule engines.
• Monitor and track key performance indicators (KPIs) to measure the impact of implemented models, strategies and initiatives.
• Communicate & present insights and results to business & technical stakeholders.
• Contribute to organizational thought via blogs, articles, case studies, white papers etc.
• Work with large, complex data sets, solving difficult, non-routine analysis problems with advanced data science methods.
• Applies (or develops if necessary) tools and pipelines to efficiently collect, clean, and prepare massive volumes of data for analysis.