https://joyston1805.github.io/blog Business Analytics student working toward ML deployment — the part after the notebook, where a model gets packaged, served, monitored, and actually used. Grounded in real production data: manufacturing yield, packaging waste, and forecasting. en-us https://joyston1805.github.io/blog/baregg-tunnel-forecasting https://joyston1805.github.io/blog/baregg-tunnel-forecasting Tue, 10 Mar 2026 00:00:00 GMT Before you can claim a forecasting model is good, you have to prove it beats doing almost nothing. Here's how that played out with three years of tunnel traffic data. r forecasting time-series https://joyston1805.github.io/blog/atticus-overpacking-case-study https://joyston1805.github.io/blog/atticus-overpacking-case-study Sun, 01 Feb 2026 00:00:00 GMT A 2% overpacking buffer sounded fine on paper. The Excel model said otherwise — and turned into a standing KPI report for operations leadership. case-study excel process-improvement