Highly skilled and results-oriented Data Scientist with 8 years of combined academic and professional experience in developing, testing, and validating AI/ML models across data-rich, process-driven environments. Proven e…
Highly skilled and results-oriented Data Scientist with 8 years of combined academic and professional experience in developing, testing, and validating AI/ML models across data-rich, process-driven environments. Proven expertise in predictive analytics, model optimization, and statistical validation frameworks supporting industrial automation and grid-related applications. Skilled in Python, SQL, and ML frameworks (TensorFlow, PyTorch, Scikit-learn) for end-to-end model design, testing, and deployment on cloud platforms including AWS and Azure. Proficient in Python, TensorFlow, PyTorch, and Scikit-learn for model development, testing, and deployment. Experienced in feature engineering, EDA, and building scalable ML pipelines that support clinical decision-making and operational efficiency. Adept at collaborating with cross-functional engineering teams to ensure models meet performance, reliability, and operational standards.
Developed and validated AI/ML models for healthcare and life sciences projects focused on predictive analytics and automation.
Performed EHR and claims data preprocessing, exploratory analysis, and model building using Python and TensorFlow.
Collaborated with cross-functional research and data engineering teams to design reproducible, high-quality analytical workflows.
Implemented NLP pipelines to extract insights from clinical text, contributing to process optimization and real-world healthcare applications.
Applied best practices in healthcare data governance, ensuring compliance with privacy and interoperability standards.
Deployed ML models on cloud platforms (Azure ML, AWS SageMaker) and evaluated performance using rigorous testing frameworks.
Engineered automated ETL pipelines using Python and SQL, reducing data processing time by 40% and enabling real-time analytics.
Developed and validated AI/ML models for healthcare and life sciences projects, Performed EHR and claims data preprocessing, exploratory analysis, and model building using Python and TensorFlow, Collaborated with cross-functional research and data engineering teams, Implemented NLP pipelines to extract insights from clinical text, Deployed ML models on cloud platforms (Azure ML, AWS SageMaker)
Developed and optimized complex SQL queries, views, and stored procedures to support IT analytics, automation, and client reporting.
Designed experiments and conducted data-driven analyses to validate business hypotheses and enhance enterprise decision-making.
Performed spend and market analysis using SQL and Power BI, improving marketing ROI, lead quality, and client sales by ~5%.
Automated KPI and business reporting using SQL, Tableau, and Power BI, increasing accuracy and eliminating manual processes.
Built predictive models to forecast sales and demand, improving forecast accuracy by 10% and optimizing inventory planning.
Created and published Power BI dashboards with DAX calculations, ensuring secure real-time data access via Enterprise Gateways.
Delivered actionable insights for strategy development, market expansion, and product innovation using advanced Excel and BI tools.
Developed and optimized complex SQL queries, views, and stored procedures, Designed experiments and conducted data-driven analyses, Performed spend and market analysis using SQL and Power BI, Built predictive models to forecast sales and demand, Automated KPI and business reporting using SQL, Tableau, and Power BI
In the customer churn prediction project, I worked as a Data Scientist owning the end-to-end ML lifecycle. My responsibilities included understanding the business problem, designing the data pipeline, performing feature engineering, building and tuning models, validating results with business teams, and finally deploying and monitoring the model in production.”Tools & Technologies Used:Data & ETL: Python, SQL, Pandas, NumPyModeling: Scikit-learn, TensorFlow/Keras (for DNN)ML Techniques: Logistic Regression, Random Forest, XGBoost, and a Deep Neural NetworkEvaluation: ROC-AUC, Precision@TopK, Recall, F1-score, Confusion MatrixExplainability: SHAP for feature importance and model transparencyDeployment & Cloud: AWS SageMaker (batch scoring & endpoints)Visualization & Reporting: Power BI for business dashboardsKey Achievements:Built a production-ready churn prediction model that achieved around 86% accuracy and strong ROC-AUC, with high recall for high-risk customers.Designed a system that prioritized the top 5–10% highest-risk customers, enabling targeted retention campaigns instead of blanket outreach.Reduced churn in the treated segment by ~18%, validated through A/B testing.Automated data ingestion and scoring pipelines, significantly reducing manual effort and enabling daily churn risk reporting.Improved stakeholder trust by using SHAP explanations to clearly show why customers were predicted to churn.
نظام التوظيف التشغيلي المعتمد على الذكاء الاصطناعي أولاً، الذي يوحّد ويؤتمت دورة التوظيف بالكامل للمؤسسات الحديثة حول العالم.
د.جوب منطقة حرة ذ.م.م. 2026 © جميع الحقوق محفوظة
