Track record

Built for operators, founders, and teams shipping under pressure.

My background is in practical machine learning: systems that support pricing, forecasting, recommendations, and planning in environments where reliability, latency, and business clarity matter.

Production forecasting and demand planning Pricing, recommendation, and operational decision systems Applied AI leadership, hiring, and mentorship Model deployment, stakeholder alignment, and pragmatic execution

ShipBob

February 2022 - Present

Lead Data Scientist

Scaled forecasting and operational intelligence across a fast-changing fulfillment network.

  • Replaced hundreds of custom forecast models with a more scalable machine learning approach that brought site-level error down from 30%+ to under 15%.
  • Built predictions that support labor planning, automated inventory placement, zone skipping, and other business-critical workflows.
  • Added anomaly detection, promotion adjustments, stock-out corrections, and other practical layers needed for reliable real-world performance.
  • Partnered across technical and business stakeholders while mentoring scientists and engineers into stronger builders.

Coyote Logistics

June 2021 - February 2022

Senior Data Scientist

Owned real-time pricing systems where quality and uptime had direct financial consequences.

  • Maintained and improved machine learning and statistical models powering live pricing and several adjacent business-critical services.
  • Led development for automated tender acceptance and a market-cost pricing service that matched the best ensemble error while using only five common shipment inputs.
  • Built scalable REST services on AKS with high-throughput batch endpoints and explainability features for human review.
  • Interviewed, hired, and mentored new team members as the group expanded from a small core team into a larger function.

Coyote Logistics

July 2017 - June 2021

Data Scientist

Delivered pricing and recommendation models that were useful in production, not just accurate offline.

  • Deployed pricing models using ensemble methods, gradient boosting, quantile regression, and other practical approaches.
  • Helped tune recommendation systems for freight matching and demonstrated measurable lift in production settings.
  • Implemented explainability endpoints that translated model behavior into human-readable reasons, increasing trust and actionability.

Coyote Logistics

July 2015 - August 2017

Data Science Analyst

Started in forecasting and experimentation while learning how data products succeed inside real organizations.

  • Built and maintained enterprise forecasts using statistical methods such as ARIMA and ETS across a range of business accounts.
  • Automated freight matching workflows with R and Python while collaborating closely with DBAs, data scientists, and software engineers.
  • Designed and led A/B testing to evaluate recommendation approaches for a live matching application.

RAR Enabled

January 2015 - July 2015

Data Analyst

Applied predictive modeling in a noisy domain where positive outcomes were rare and precision mattered.

  • Led model development across multiple debt portfolios spanning healthcare, utilities, and other domains.
  • Built classification and regression models to estimate payment likelihood and expected value in highly imbalanced data.
  • Deployed a scoring workflow for incoming placements and used statistical analysis to improve collection strategy.