Living Goods, Nairobi – Global Director Performance, Evidence and Insights Feb 2023 – Current

• Led strategic reorganization of Monitoring & Evaluation, Research, and Data Science departments to create an integrated data-driven community health framework, optimizing cross-functional collaboration and analytical capabilities.
• Spearheaded a comprehensive 7-arm randomized controlled trial (RCT) to evaluate community health worker compensation models, employing A/B testing methodologies to identify optimal incentive structures for improved healthcare delivery outcomes.
• Led development of advanced predictive analytics models using Python, successfully implementing XGBoost algorithms to forecast immunization patterns and identify at-risk mothers for postnatal care dropout, significantly improving preventive healthcare interventions.
• Conducted advanced analysis of organizational compensation data to evaluate correlation between performance bonuses and desired behavioral outcomes, providing data-driven recommendations for incentive structure refinements.
• Designed and implemented an automated monthly reporting pipeline, incorporating cutting-edge LLM technology ("Ask a Metric") to democratize data access and enhance data utilization across the organization, significantly reducing manual reporting effort.
• Pioneered the integration of machine learning and natural language processing solutions to transform organizational data accessibility, enabling stakeholders to extract actionable insights through conversational AI interfaces.
• Executed in-depth performance analytics across multiple departments, leveraging statistical methodologies to identify key performance drivers and optimize resource allocation for community health initiatives.
• Developed and implemented comprehensive data governance frameworks to ensure ethical handling of sensitive performance and compensation data while maintaining analytical rigor and accessibility.

Intern

Data Science Intern – AtliQ Technologies, Virtual
October2024 – Nov 2024

• Assisted in developing predictive models using Python and Scikit-learn for a multi classs price prediction analysis. Engaged in data cleaning, feature selection, and hyperparameter tuning, resulting in a model with 85% accuracy.
• Worked closely with senior data scientists to optimize machine learning pipelines by implementing cross-validation and grid search techniques, improving model performance by 10%.
• Conducted exploratory data analysis (EDA) on a large retail dataset using Pandas and Matplotlib to uncover trends and patterns, providing key insights to drive mark entry strategy.
• Participated in feature engineering efforts by creating custom metrics and derived features that enhanced model predictions for customer segmentation.
• Built interactive visualizations in Tableau to communicate data-driven insights to stakeholders, ensuring a clear understanding of key performance indicators and model outputs.