James W.

I’m a CPA-credentialed Data Engineer and Data Scientist with 10+ years’ experience designing and scaling end-to-end data platforms, AI/ML workflows, and Power BI solutions for Fortune 100 and growing SMBs. I bridge deep technical expertise (Python, PySpark, SQL, Azure Data Factory, Microsoft Fabric, dbt) with a finance background to deliver reliable ETL pipelines, optimized data warehouses, predictive models, and interactive dashboards that drive strategic decision-making.

Core Expertise

Data Science & Machine Learning: Feature engineering, model training (classification, regression, survival analysis), deployed ML pipelines, probability calibration, threshold optimization, drift monitoring, SHAP explainability

Data Engineering & ETL: Python/PySpark, SSIS, ADF, incremental loads, CDC, schema drift handling

Cloud Data Platforms: Microsoft Fabric, Synapse Analytics, Azure SQL, AWS Redshift, S3

Database Design: Star/snowflake schemas, partitioning, indexing, performance tuning

BI & Reporting: Power BI modeling (DAX, composite models, RLS), incremental refresh, paginated reports

Automation & Integration: Power Automate, Power Apps, REST/API workflows

Finance & FP&A: Financial data modeling, forecasting, reconciliation, audit trails

Highlights

Architected a Fabric Lakehouse and Spark pipelines to consolidate numerous financial sources accelerating month-end close by 40%

Developed end-to-end ML pipelines for client reactivation and churn prediction models, including automated retraining and performance dashboards using SHAP explainability

Led Big 4 FP&A platform redesigns, embedding governance, predictive analytics, and self-service BI across global teams

Delivered turnkey BI and data engineering solutions for healthcare, retail, and professional services, including integrating clinical data for AI-driven insights

Let’s connect to discuss how I can streamline your data architecture, implement AI/ML solutions, and empower your team with insights that scale.