Overview
DumpsterData brings data engineering, statistical modeling, and product development together in a commercial waste pricing estimator. As founder and AI/ML developer, I am building the platform from concept through a deployed website.
Problem
Commercial waste pricing is sensitive to location and service context. Comparing prices requires bringing disparate inputs into a consistent form and accounting for location-sensitive pricing factors.
Technical Approach
Data integration and normalization establish a consistent foundation for estimation. Geospatial data and statistical modeling support location-sensitive estimates, connecting analytical work with a practical user-facing application.
Architecture / Methods
The full-stack product combines Python and FastAPI with a Next.js web application. Data engineering supports the integration and preparation of inputs, while geospatial modeling informs the commercial waste pricing estimator.
Outcomes
The website is deployed at dumpsterdata.com. It provides a concrete application of data integration, pricing estimation, and full-stack development. Quantitative accuracy and business-impact results are not presented in this case study.