About Us
GSK is a pre-eminent pharmaceutical and healthcare company dedicated to leading a healthcare revolution. The Decision Science & AI team applies advanced capabilities to drive innovation, augment decision making, and better serve patients, healthcare professionals, and consumers through disruptive approaches in R&D and commercial business processes.
We are seeking a highly skilled and experienced Senior Data Scientist to join our team to support the US Specialty Business Unit. This role is ideal for individuals passionate about leveraging advanced analytics and predictive modeling to drive better patient outcomes and support strategic decision-making in the healthcare sector.
Responsibilities
- Patient-Level Data Analysis: Work hands-on with anonymized patient-level data (APLD) and prescriber/account level datasets (e.g. Xponent, Drug Distribution Data) to extract insights, ensuring data quality and integrity while integrating data from diverse healthcare sources.
- Cohort Identification & Tracking: Develop and refine business rules to identify eligible patient/prescriber cohorts and implement methodologies for longitudinal tracking of these cohorts over time.
- Predictive Modeling:
- Develop prescriber/patient look-a-like models to support targeting and sizing exercises.
- Develop promotional response, clustering/segmentation models to evaluate effectiveness of strategic decisions.
- Build, test, and deploy time series forecasting models to predict trends in HCP prescribing patterns.
- Model Documentation & Knowledge Sharing: Maintain thorough documentation of data analysis processes, model development, and insights. Develop clear presentations and reports to effectively communicate findings to team members.
- Cross-Functional Collaboration: Partner with data engineers, Insights & Analytics teams, and external stakeholders to align analytical solutions with organizational goals. Support ad-hoc analytical requests and contribute to strategic data initiatives.
- Analytical Reporting & Dashboarding: Create and maintain dynamic dashboards and reports in traditional BI tools (e.g. Power BI, Tableau) and GenAI driven tools (e.g. Databricks Genie) to translate complex data findings into actionable business insights for commercial stakeholders.
- Innovation & Continuous Improvement: Explore and evaluate emerging analytical techniques, including GenAI capabilities where applicable, to enhance existing methodologies and drive innovation in patient analytics.
Basic Qualifications
- Experience: 4-7 years of experience in pharmaceutical analytics or a related domain, with a strong focus on patient-level data analysis.
- Education: Bachelor’s degree in Engineering, Statistics, Mathematics, Computer Science, or a related quantitative field.
- Technical Proficiency:
- Proficiency in programming languages and data analysis tools such as Python, R, PySpark, and SQL.
- Solid experience in developing predictive modeling techniques (look-a-like models, time series forecasting, regression, clustering).
- Proven ability to design, implement, and refine business rules for the identification and tracking of patient cohorts within claims databases.
- Familiarity with working in Azure cloud environment, using distributed compute for large datasets, and version control tools (e.g. Git).
- Data Proficiency: Expertise in handling large-scale pharmaceutical datasets (e.g., Anonymized patient level data - APLD) and applying statistical and machine learning methods to drive actionable insights.
- Data Storytelling & Communication: Demonstrated ability to translate complex data insights into clear, compelling narratives and presentations. Adept at communicating technical findings in a relatable manner to non-technical stakeholders.
- Autonomy & Prioritization: Proven ability to work independently, manage multiple projects/workstreams, and prioritize effectively in a fast-paced, data-driven environment.
- Problem-Solving & Collaboration: Demonstrated ability to troubleshoot complex data issues, optimize system performance, and work effectively within a team environment.
Preferred Qualifications
- Machine Learning & MLOps: Basic understanding of machine learning workflows and experience with ML pipelines or MLOps practices is a plus.
- Advanced Modeling Experience: Hands-on experience in developing advanced machine learning models using deep learning techniques/architectures (e.g. CNNs, Transformers, LSTMs) and associated frameworks (e.g. Keras, PyTorch, TensorFlow) is a plus.
- Data Visualization & Reporting: Exposure to traditional visualization/reporting tools (e.g., Power BI, Tableau) and GenAI tools (e.g. Databricks Genie) to support data-driven decision-making is beneficial, but not a primary focus.
- Industry Certifications: Professional certifications in Data Science or related fields are advantageous.