Accomplished Research Scientist at ICON plc with expertise in Python and R programming, driving impactful data analysis and statistical modeling. Proven ability to mentor teams and enhance processes, exemplified by automating ADA calculations, saving significant time. Adept at collaboration and delivering submission-ready reports to regulatory agencies, ensuring compliance and quality.
Phishing Classifier, GBM with feature engineering, optimized for F1-score COVID-19 API Dashboard, Real-time monitoring in Power BI Vaccine Response, Logistic regression & ANOVA on antibody data Fraud Detection, SMOTE, Random Forest, SHAP Missing Data Analysis, Simulated MCAR/MAR/MNAR, MICE & regression imputation Boston Housing, Boosted tree regression (R2 = 0.87) A/B Testing Simulator, Power curve tool built in R Wine Clustering, PCA, factor analysis, and K-means A/B ML, Conducted A/B testing on machine learning models to evaluate their accuracy and latency.
Title: Data Scientist/Analyst | Biostatistician | Research Scientist
linkedin.com/in/luke-wamalwa-839624292, github.com/lukahere007