Data Scientist - Insurance Analytics

Role Overview:

The Data Scientist will be a key member of the Analytics team, collaborating with data scientists, actuaries, and business analysts across Underwriting, Product, Finance, and Technology. The role involves developing and implementing advanced analytics and machine learning solutions to strengthen underwriting models, improve risk selection, optimize pricing, and support pricing strategies across the insurance business.

The ideal candidate will have a strong quantitative background, hands-on experience in statistical modeling and machine learning, and the ability to translate complex data into actionable business insights.

Key Responsibilities:

- Develop, train, test, deploy, and monitor machine learning models to address business challenges in insurance analytics.

- Build and enhance analytical models that support underwriting decisions, risk assessment, pricing optimization, and pricing strategy.

- Acquire, integrate, clean, and transform data from diverse sources using APIs, SQL, NoSQL, and Python.

- Apply statistical techniques, including descriptive, inferential, and Bayesian statistics, time-series analysis, and applied probability, to derive meaningful insights.

- Conduct experimentation and A/B testing to evaluate model performance and improve business outcomes.

- Apply machine learning algorithms and mathematical principles to solve complex analytical problems.

- Leverage Natural Language Processing (NLP) techniques to develop data-driven solutions for relevant business use cases.

- Develop data visualizations and analytical outputs using Python, R, and other suitable tools.

- Contribute to the Model Development Life Cycle (MDLC), ensuring robust model development, validation, deployment, and monitoring.

- Work with CI/CD/CT pipelines and tools such as Jenkins, CloudBees, and Harness to support automated model deployment and testing.

- Collaborate with cross-functional teams to translate business requirements into scalable analytical solutions.

- Leverage cloud technologies and computing frameworks to support data science and machine learning workflows.

Required Skills and Qualifications:

Education:

- Master's degree or Ph.D. in Mathematics, Statistics, Engineering, Econometrics, Physics, Computer Science, Actuarial Science, Data Science, or another relevant quantitative discipline.

Data Acquisition and Transformation:

- Hands-on experience acquiring data from multiple sources using APIs, SQL, and NoSQL databases.

- Strong skills in data extraction, transformation, cleaning, and processing using SQL, NoSQL, and Python.

- Experience with data visualization using tools and libraries in Python and R.

Statistics and Mathematical Computing:

- Strong understanding of calculus, multivariable calculus, linear algebra, differential equations, probability, and statistics.

- Knowledge of descriptive, inferential, Bayesian, and applied statistical methods.

- Experience with time-series analysis, statistical experimentation, and hypothesis testing.

- Ability to apply mathematical and statistical concepts to solve complex business problems.

- Understanding of computer science fundamentals, programming methodologies, and cloud computing.

Machine Learning and NLP:

- Strong understanding of machine learning theory and the mathematical foundations of machine learning algorithms.

- Hands-on experience building, training, testing, validating, and monitoring machine learning models.

- Expertise in applying machine learning techniques to real-world business problems.

- Knowledge and practical experience in Natural Language Processing (NLP).

Model Deployment and MLOps:

- Understanding of the Model Development Life Cycle (MDLC).

- Experience with model deployment, testing, monitoring, and continuous improvement.

- Familiarity with CI/CD/CT pipelines and tools such as Jenkins, CloudBees, and Harness.

- Experience with A/B testing and model performance evaluation.

Programming Languages:

- Python

- R

- SQL