Yordanos Girma Ayele

• Data Validation

Implemented KolmogorovSmirnov and Chi-square goodness-of-fit tests in Python to validate survey distribution. Ran Monte Carlo simulations to measure Type I/II error rates and automated exact p-value estimation.

Demonstrated ability to validate large datasets against benchmarks, mirroring clinical trial data checks.

• Traffic Incident Data Warehouse

Designed and implemented ETL pipelines (SSIS, Python) to ingest and clean traffic incident records Built OLAP cubes (SSAS) for fast, multidimensional analysis and reporting.Applied data quality checks to ensure consistency across large, heterogeneous datasets.

• UK Road Accident Analysis

Preprocessed and explored 1.6 million records of accident data; engineered features for analysis.Built predictive models (logistic regression, random forests) and clustering to uncover hidden patterns Collaborated in translating raw data into actionable insights, similar to preparing datasets for clinical research.

• Customer Data Segmentation & Dashboards

Conducted audience segmentation for a nonprofit's Google Ad Grants campaigns. Designed performance dashboards (Power BI, Python) to track and optimize campaign outcomes. Showcased ability to present data clearly to non-technical stakeholders.

• Designed and maintained customer data pipelines (Python, SQL) to ensure accuracy, reliability, and availability of service-related datasets.
• Implemented data validation and quality checks to improve consistency of customer records across operational systems.
• Collaborated with both technical IT teams and customer-facing operations teams to translate requirements into actionable data solutions.
• Created dashboards and automated reports (Power BI, SQL Server) to monitor service performance and support data-driven decision-making.
• Resolved real-time data issues by troubleshooting inconsistencies and ensuring uninterrupted operations.
• Documented and optimized data management processes, contributing to compliance and best practice standards.