Kategorie: Data Science
-
Sole Source: The $900k Median Problem Your Dual-Source Checkbox Won’t Fix
The dual-source flag teams buy to feel safe moves the median cost of a disruption about $44k. In the wrong direction. The dependency nobody flags moves it $474k.
-
The Resilience Ladder: Why the Things You Buy to Feel Safe Don’t Save You
I pulled 3,000 disruptions to find what separates firms that survive a shock from firms that bleed. The dual-source checkbox wasn’t it.
-
I Gave an AI Agent the Reorder Button: It Rebuilt the Bullwhip in 250 Days
An AI agent with the reorder button hit ~100% fill rate and looked like a star. Then I measured what it dumped on its suppliers.
-
Global Forecasting with XGBoost in R: A Walmart Weekly Walkthrough
A hands-on walkthrough of global XGBoost forecasting in R with tidymodels and modeltime, applied to the Walmart weekly sales dataset. What the feature importance reveals, when ML earns its complexity, and when ETS or SNAIVE quietly wins.
-
I Ran 6 Models on Real Demand Data — Here’s How I Picked the Winner
Six forecasting models, one real demand series, one honest horse race. Here’s the model that won — and the metric that made the choice unambiguous.
-
Is Your Forecast Any Good? The Forecaster’s Toolbox
Four acronyms decide whether you trust a forecast: MAE, MAPE, RMSE, MASE. Here is when each one lies to you — and the one benchmark that catches them all.
-
Three Equations From the Navy in 1957: Why Holt-Winters Still Runs Your Forecast Engine
Holt-Winters wasn’t born in a statistics lecture — it was written for the U.S. Navy in 1957 to solve an inventory problem. Nearly seven decades later, three recursive equations still beat most of the software sitting on top of your ERP.
-
Taking the Engine Apart: Time Series Decomposition for Supply Chain Forecasters
Every time series is a cocktail of trend, seasonality, and noise. Decomposition is how you separate the ingredients — and once you can see each one, choosing the right forecast model stops being a guessing game.
-
Your Line Chart Is Hiding 8 Patterns: How to Find Them with fpp3
Four datasets. Identical statistics. Completely different shapes. If you’re not plotting your demand data before forecasting it, you’re flying blind — and fpp3 gives you the visual toolkit to see what your spreadsheet hides.
-
Your First Forecast in 15 Minutes: A Supply Chain Pro’s Guide to R, RStudio & FPP3
You convinced your boss R is better than Excel. Now what? Install it, load fpp3, and produce your first real forecast — all before your coffee gets cold.
-
Stop Forecasting in Excel: Why R Is the Only Serious Tool for Supply Chain Demand Planning
Excel can’t do seasonality, model comparison, or prediction intervals without heroic effort — R does all three in six lines of code. Here’s why April is the month you finally make the switch.
-
I Scored 10 Fortune 500 Giants as Suppliers: Wall Street Would Not Agree
I applied a multi-dimensional supplier risk framework to 10 of the largest Fortune 500 companies — using real public data. The company with the best credit rating scored as the riskiest supplier. Your neighborhood pharmacy landed at number two. Here’s every score, every data source, and the R code to run it on your own…
-
Where Should Your Warehouse Be? 12 Lines of R Code Have the Answer
Most companies pick warehouse locations based on gut feel, real estate deals, or where the CEO lives. The optimal location — the one that minimizes total weighted transport cost — can be found with 12 lines of R code. The answer is rarely where you think.
-
FPP3: Stop Guessing Which Forecast Model Works — Measure It
Rob Hyndman’s fpp3 ecosystem lets you fit, compare, and evaluate multiple forecasting models in three lines of R code — here’s why supply chain teams should stop fighting Excel and start using a real framework.
-
Prophet: The Forecasting Tool That Actually Makes Sense to Non-Statisticians
Meta’s Prophet gives supply chain teams accurate demand forecasts without requiring a statistics degree — here’s how it works, where it shines, and where it doesn’t.