Senior

Data Scientist Role and Responsibilities

Credit Saison India is seeking a Data Scientist to collaborate with stakeholders across the organization, identifying opportunities to utilize internal and external data for developing business solutions. You will be instrumental in creating a data science use case roadmap for specific problem areas or capabilities. Your responsibilities will include mining and analyzing data from company databases to optimize and enhance products. You will develop comprehensive credit risk scorecards and models, covering application, behavior, and collection stages, employing techniques such as linear and logistic regression, random forest, boosting/bagging trees, and dimensionality reduction algorithms. As a data strategist, you will identify and integrate new datasets to leverage product capabilities and work closely with the engineering team to execute data product development. This role involves enhancing data collection procedures, processing, cleansing, and verifying data integrity for analysis. You will conduct data exploration to uncover relationships and patterns, developing visualizations to represent these findings. Proficiency in data mining using state-of-the-art methods, feature selection, and building/optimizing classifiers with machine learning techniques is essential. A deep understanding of the algorithmic and inferential aspects of statistical analysis is required, along with the ability to evaluate and apply new algorithms from research. You will build training pipelines for production environments and develop plans for continuous model iteration and refinement. Providing input for design, quality assurance parameters, and supporting online model implementation is also a key part of the role. Furthermore, you will contribute to determining infrastructure requirements and management for model deployment, lead debugging of data pipelines and model behavior in production, and develop dashboards for tracking and communicating model impact.

Required Skills and Qualifications

We are looking for candidates with 2 to 6 years of experience in data manipulation and statistical model building. A Bachelor's, Master's, or PhD degree in Statistics, Mathematics, Computer Science, or a related quantitative field from a top-tier college is required. Strong problem-solving skills with a focus on product development are essential. Excellent written and verbal communication skills are needed for cross-team coordination. You should possess strong applied statistics skills, including distributions, statistical testing, and regression. Proficiency in scripting and programming languages such as Python, PySpark, and SQL is crucial. A thorough understanding of machine learning techniques and algorithms, including k-NN, Naive Bayes, SVM, Xgboost, Decision Forests, and artificial neural networks, along with their real-world applications and limitations, is expected. Knowledge of deep learning techniques is a plus. Experience with common data science toolkits like NumPy, Pandas, Scikit-learn, TensorFlow, and Keras is required, as is familiarity with data visualization tools such as Tableau. Experience in credit, risk, or collections management (e.g., Application Scorecards, Behavior Scorecards, Collection Scorecards, Loan Pricing, Propensity Models, Cross-Sell Models) is a strong advantage. Experience with NoSQL databases such as MongoDB, Cassandra, or HBase is desired. Familiarity with distributed data/computing tools like Map/Reduce, Hadoop, Hive, and Spark is a significant plus. Hands-on experience with cloud computing and big data platforms like AWS S3, SageMaker, Athena, and Databricks is preferred.