Chege John
Results-driven Data Analyst with strong experience translating complex datasets into clear, actionable insights that support business growth and operational efficiency
Hire this person
Send a job offer directly to this candidate
About
Results-driven Data Analyst with strong experience translating complex datasets into clear, actionable insights that support business growth and operational efficiency. Skilled in Python, SQL and BI tools with a focus on data cleaning, transformation, visualization and predictive modeling. Proven ability to design scalable ETL pipelines, perform in-depth exploratory data analysis and deliver insights that inform strategic decision-making at senior levels.
Experienced in customer segmentation, performance optimization and building data products that improve efficiency and drive measurable outcomes. Brings a collaborative approach to working with cross-functional teams to align data solutions with business goals. Holds a BSc in Computer Science, is pursuing a Master's in Computer Science and has completed a Data Science certification, with a strong interest in applying data to solve real-world problems and support innovation.
Experience
Senior Data Analyst/Data Engineer at Yellow Card (2022-01 – 2025-12)
- Designing and deploying scalable ETL and ELT pipelines using Airflow, PySpark and dbt to process hundreds of GBs daily for risk adjustment coding and chart retrieval workflows, reducing end-to-end latency.
- Building and optimizing dbt models integrated with Snowflake and Databricks to enable HCC-level aggregation, hierarchy resolution and accurate cohort analysis across Medicare Advantage and Medicaid populations.
- Developing advanced SQL analytics and Python automation to compute risk scores and cohort prevalence across HCC, RxHCC, HHS-HCC and CDPS models, improving forecasting accuracy and ROI scenario planning.
- Orchestrating end-to-end data workflows using Airflow DAGs for chart retrieval, risk adjustment coding handoffs and HEDIS abstraction loads, ensuring consistent SLA adherence and timely delivery to stakeholders.
- Engineering interactive dashboards in Power BI and Tableau to visualize coding productivity, diagnosis trends and QA performance, enabling real-time, data-driven decision making.
- Leading large-scale data migrations across SQL Server, Oracle and Snowflake environments, maintaining 99.9 percent data integrity while enforcing HIPAA-compliant access controls and audit logging.
- Transforming ad hoc analyses into scalable data products by developing reusable dbt packages, SQL macros and standardized templates, significantly improving reporting efficiency across clients.
- Implementing automated data quality and validation frameworks using Python and SQL to detect anomalies, reduce rework and enhance coding accuracy and data reliability.
- Collaborating with cross-functional teams including clinical coders, product managers and clients to define risk adjustment methodologies, align reporting standards and strengthen stakeholder engagement.
- Introducing near real-time data streaming solutions using Kafka and Spark Structured Streaming and mentored junior analysts on SQL, dbt and risk adjustment analytics, improving team capability and operational responsiveness.
Senior Data Analyst (Automation & Risk Analytics) at Ngeni Labs (2020-01 – 2021-12)
- Engineered and optimized ETL and ELT workflows using Talend and Python for chart retrieval and clinical abstraction pipelines, reducing processing time from 8 hours to 2 hours and improving overall data throughput.
- Designed predictive analytics solutions for cohort forecasting and program optimization, leveraging historical risk scores and demographic trends to model ROI across multiple scenarios.
- Developed and maintained data retrieval, enrichment and integration logic within Marshalls Data Lake, delivering actionable insights through Power BI and Tableau dashboards for operations and compliance teams.
- Built and implemented SQL and Python-based QA and validation frameworks to ensure accuracy of risk adjustment coding and HEDIS abstraction data, including diagnosis hierarchies, prevalence calculations and migration integrity.
- Automated reporting workflows by creating standardized templates and API-driven processes, eliminating 40 percent of manual effort while improving scalability and consistency of client deliverables.
- Translated stakeholder requirements into structured reporting methodologies and trained cross-functional teams on Excel, SQL and risk model interpretation, while tracking productivity and quality KPIs to drive continuous improvement.
Data & Reporting Engineer at University of Nairobi (2018-01 – 2019-12)
- Orchestrated AWS CloudFormation and Elastic Beanstalk deployments to host Python-based reporting services, shortening deployment cycles and improving release efficiency for clinical operations.
- Optimized data storage architectures and query performance, increasing retrieval speeds by 25 percent while reducing infrastructure costs for production analytics workloads.
- Developed Flask-based REST APIs integrated with PostgreSQL to deliver daily transaction and coding data feeds, enabling seamless downstream BI reporting and analytics.
- Automated data ingestion and timestamping pipelines to support engineering and clinical teams, accelerating chart retrieval processes and improving coding throughput.
- Implemented monitoring and alerting frameworks using Elasticsearch and Kibana, maintaining 99.9 percent system uptime and proactively identifying anomalies in data ingestion and coding workflows.
- Collaborated within Agile cross-functional teams to translate clinical and regulatory requirements into scalable data models and validation processes, while presenting insights through clear reports and visualizations to support strategic decision-making.
Education
Master of Science in Computer Science – Multimedia University (2023-01)
Certificate in Data Science – Moringa School (2023-01 – 2023-12)
Bachelor of Science in Computer Science – Masai Mara University (2019-12)
