Bridging the gap between advanced predictive analytics, scalable ML architecture, and cross-functional business execution.
Drawing on over a decade of experience across banking, insurance, and tech manufacturing, I specialize in applying cross-industry predictive frameworks to engineer modern credit and growth strategies. With expertise in Python, Databricks, and SQL, I design end-to-end analytical pipelines. Beyond the code, I thrive as a strategic bridge—translating complex data models to secure executive buy-in, mentoring technical teams, and partnering directly with marketing and business units to execute highly targeted campaigns.
Case studies demonstrating my ability to navigate complex enterprise data systems, engineer predictive features, and collaborate across teams to optimize business outcomes.
The Challenge: Traditional credit propensity models rely on static demographic data, missing dynamic financial behaviors.
The Solution: Architected a novel feature engineering framework using transactional data to quantify Share of Wallet and Relationship Depth. Translated these complex technical signals into business strategies for executive stakeholders.
The Impact: Created a scalable blueprint to identify high-value, low-risk clients, partnering directly with Marketing and Business teams to deploy these insights into live Authorized User campaigns.
The Challenge: Disconnected enterprise data science teams building redundant predictive models, leading to governance risks and wasted cloud compute.
The Solution: Conducted an architectural audit of a proposed propensity model build. Discovered an overlapping model and executed a strategic handover, consolidating custom logic into the central team's production pipeline while mentoring junior analysts on architectural standards.
The Impact: Secured executive buy-in to halt redundant development, eliminated data governance risks, and optimized enterprise ML resources across multiple silos.
The Challenge: Traditional actuarial methods rely on broad averages, leading to over-reserving (trapped capital) or under-reserving (P&L shocks) for liability claims.
The Solution: Architected an end-to-end PySpark ML pipeline on Databricks. Engineered a Gradient Boosted Tree model that captures non-linear risk interactions, outperforming standard GLMs, and tracked the deployment via MLflow Unity Catalog.
The Impact: Successfully segmented risk, demonstrating via decile analysis that the model accurately isolates routine claims ($3k) from severe shock losses ($35k+), enabling precise capital allocation.