Senior Analyst - Data Science - Pharmaceutical

Work on a variety of business applications including but not limited to:

- Customer Segmentation & Targeting, Event Prediction, Propensity Modelling, Churn Modelling, Customer lifecycle management and Lifetime Value Estimation, Recommender Systems, Launch Analytics, Marketing Mix Modelling and Revenue Optimization, Price Optimization

- Independently work on various steps of a data science project - Data mining and Exploratory Data Analysis (EDA), Feature Engineering, Statistical modelling, integration with AI/ML platform, visualization and result inferencing and presentation to stakeholders

- Automation of project codes and development of front-end delivery solutions

- Ensure quality and timely completion of own projects/modelling assignments, actively manage change during the project and raise any operational risk early to project lead/supervisor.

- Assist team supervisor for development of new algorithms, methods, statistical models and business models and providing insight into structured and unstructured data

- Explore and use various available pharma data sources (such as sales, contracting, promotions, social media, claims, Real-World Evidence, etc.) for enhancing the accuracy/application value of the analytical solution

- Participate in various knowledge sharing sessions that enables growth and improves quality of CTS CONEXTS deliverables across the function

- Comply with all internal functional operating procedures like time tracking, KPI tracking and reporting, and other internal systems and processes

- Comply to all Novartis operating procedures as per legal/IT/HR requirements

Job Requirements

Technical Skills:

- Statistical Modeling/Machine Learning

Must have: Statistical and Machine Learning techniques like Regression (esp., GLM, non-linear, etc.), Classification (Trees, Random Forest, Boosting, SVM, CART, etc.) Clustering, Design of Experiments, Monte Carlo Simulations, Statistical Inference, Feature Engineering, Market mix modelling, Dynamic Programming and Optimization techniques, Recommender Systems, Time Series Forecasting

Good to have: Stochastic models, Bayesian Models, Markov Chains, Deep Learning techniques on structured and unstructured data, Text mining and Natural Language Processing (NLP)

- Data mining tool and EDA for large datasets.

- Data science programing languages and querying databases: R, Python, SAS, SQL/Hive

Familiarity with Alteryx will be a bonus

- Exposure to dashboard or web-apps building using R-Shiny, Flask

Good to have:

- Exposure to AWS and ML Pipelines on cloud

- Pharmaceutical industry domain/datasets knowledge