Data Scientist

Responsibilities:

• Developed advanced analytics solutions using patient-level Real World Evidence (RWE) datasets to generate actionable insights for Pharmaceutical and Life Sciences stakeholders.
• Analysed healthcare claims and patient-level data from Optum / IQVIA / Komodo to understand treatment patterns, patient behaviour, therapy utilisation, and healthcare outcomes.
• Built patient journey analytics to identify treatment initiation, progression, switching, discontinuation and drop-off points across patient cohorts.
• Performed treatment adherence, persistence and days-on-therapy analysis to identify factors influencing patient continuation and treatment outcomes.
• Applied survival analysis techniques to evaluate time-to-event outcomes, treatment persistence and patient-level healthcare journeys.
• Developed sequence-based analytical approaches to understand longitudinal patient treatment patterns and transitions across therapies.
• Applied hypothesis testing, probability, statistics and machine learning to formulate business problems into analytical hypotheses and proofs-of-concept.
• Developed predictive and statistical models using Python and SQL, including feature engineering, model development, validation and interpretation.
• Worked with large-scale healthcare datasets involving data extraction, integration, cleansing, transformation and cohort construction for RWE analytics.
• Translated complex analytical findings into business recommendations and actionable insights for technical and non-technical stakeholders.
• Created executive-ready visualisations and analytical dashboards using Tableau, Power BI, Matplotlib and Seaborn.
• Collaborated with cross-functional stakeholders to understand business requirements, define analytical approaches, prioritise deliverables and manage project risks.
• Followed modern software engineering practices including Git/version control, peer code reviews, reusable code, documentation, refactoring and collaborative development.
• Prepared technical documentation covering business understanding, data preparation, methodology, experimentation, model validation and recommendations, following CRISP-DM-aligned practices.
• Provided technical mentorship and peer reviews to junior data scientists, improving analytical quality and development practices across the team.
• Led multiple analytical workstreams by breaking complex business problems into smaller components, allocating tasks, tracking progress and ensuring timely delivery.
• Researched emerging Machine Learning, Deep Learning, NLP, explainable AI and advanced analytics techniques and evaluated their applicability to healthcare and pharmaceutical use cases.
• Communicated analytical insights through storyboarding and structured presentations, enabling non-technical stakeholders to understand model outputs, business implications and recommended actions.