[nom]

DATA SCIENTIST/STATISTICIAN

[e-mail] | [téléphone] | Dubai, UAE | [lien]

Professional Summary

Data Scientist with six years of experience building, validating, and deploying machine learning and statistical models on large structured and unstructured datasets. Strong in Python (Pandas, NumPy, Scikit-learn) and SQL, with hands-on expertise across predictive modelling, forecasting, segmentation, NLP, and experiment design. Experienced in the full analysis lifecycle from framing ambiguous business problems through modelling, dashboards, and clear communication to technical and non-technical stakeholders with recent work in MLOps and model deployment (FastAPI, Docker, CI/CD). Known for turning data into measurable business impact.

Professional Experience

Data Scientist | IQVIA | July/2019 - February/2026

• Designed, built, and validated 20+ predictive and statistical models across global clients, improving ROI 10–20% through data-informed strategy.
• Cleaned, preprocessed, and analysed large structured and unstructured datasets using Python and SQL, building reproducible analysis workflows.
• Delivered forecasting, price elasticity, and A/B & Test-Control experiments to guide decisions and budget allocation influencing $5M+ annually.
• Performed Marketing Mix Modelling, segmentation, and clustering across 10+ therapy areas, translating business questions into measurable outcomes.
• Applied NLP and text mining to extract structured insight from unstructured trial and commercial text, supporting strategic decisions.
• Automated analysis and reporting workflows, reducing manual processing time by 40% and improving accuracy and reproducibility.
• Communicated results to technical and non-technical stakeholders, coordinating cross-functionally and across continents to drive adoption.

Intern | Department of Statistics and Economics Government of Kerala, India | 2018

• Assisted in data collection and statistical analysis for economic research projects, including data cleaning and preprocessing to ensure dataset accuracy.
• Collaborated with senior statisticians to interpret data trends and contributed to policy recommendations through detailed statistical analysis.

Core Qualifications & Skills

• Data analytics and Predictive Modeling · • · Statistical concepts and applications
• Market and Digital analytics · • · Regression and multivariate techniques
• Project management and Leadership · • · Data management and Visualization
• Survey and Questionnaire design, Market · • · Machine Learning techniques and AI research · • · Healthcare Data Analytics
• Stakeholder management, Cross- · and Strategic Insights Functional collaboration and ad-hoc
• Experimentation, A/B reporting testing, KPI analysis and
• EDA, data cleaning and transformation for structured/ unstructured data · trend/ variance analysis

Portfolio Projects

• Churn Prediction API: end-to-end ML pipeline built from scratch: data preparation, model training, FastAPI service, Dockerised, CI/CD via GitHub Actions, deployed to production (Render). Demonstrates end-to-end deployment and maintenance in a live environment.
• Fraud/Risk Classification: end-to-end fraud and risk classification pipeline handling imbalanced data, with leakage-aware feature engineering, baseline-vs-improved model comparison, and a threshold-tunable Streamlit demo. Demonstrates rigorous evaluation (precision/recall, PR-AUC) on a real-world imbalanced problem.
• Clinical NLP Classifier: scaffolded text-classification project for clinical/commercial text, extending prior NLP and text-mining work toward LLM-based document understanding and knowledge extraction.
• Healthcare RCM Analytics: synthetic data generation, SQL analysis, statistical scripting, and interactive dashboard deployed to GitHub Pages.

Education

Loyola College| Chennai, India | 2019

Master’s degree in Statistics

St. Teresa's College| Kochi, India | 2017

Bachelor of science in Mathematics

Certifications and Training

• Power BI - Level 100 & Level 200 (IQVIA internal certification)
• Google Analytics Certification (2026) - Jul 2026 - Jul 2027

Technical Expertise

• Programming Languages: R, Python, SAS and · • · Statistical Techniques: Controlled SQL, Google Analytics (GA4) · Experiment Design (Test & Control),
• Commercial analytics: revenue growth, pricing · Regression, Clustering, forecasting, analysis, competitor monitoring, and market · Market segmentation, NLP and other positioning · Machine Learning techniques & concepts
• Understanding business metrics, KPIs, and how · • · Expertise in data manipulation tools like Excel data analysis supports business decisions · • · Experience with statistical software (R, SAS, SPSS)
• Data Visualization and analysis: Power BI,
• Platforms: AWS (Redshift and S3), MySQL,

Excel and Think-cell

CRM systems

• MLOps & Cloud: Docker, FastAPI, GitHub

Actions (CI/CD)