CAT Used Price Advisor
I lead the ML models behind this dealer-facing tool, which prices more than 70,000 pieces of equipment worth over $12B.
A handful of projects I'm proud of, spanning equipment pricing, genomics, and plant breeding — the kind of work I keep coming back to when explaining what I actually do all day.
I lead the ML models behind this dealer-facing tool, which prices more than 70,000 pieces of equipment worth over $12B.
I built an index that separates real market price movement from quality differences, now used by CAT Financial and senior leadership to sharpen pricing strategy across sale channels.
I developed an improved forecasting model that predicts industry size five quarters out, using price-trend data from auction and retail markets along with consumer behavior.
I productionized pipelines processing 3TB of genomic data a day, cutting manual effort by 70% and making downstream analytics faster and more reliable.
I architected a BigQuery repository that became the team's single source of truth for crop analytics, and the foundation for everything built on top of it since.
I developed an imputation method that took usable data return from 30% to 92% per feature — a meaningful jump in how much of the data we could actually put to work.
I applied Gaussian Mixture Models to improve true variant detection by 70% in genomic datasets, strengthening the data quality everything downstream depended on.
During my PhD, I mapped insect-resistance genes in wheat using mixed-model regression — work aimed at breeding varieties that need less pesticide.