InPhroNeSys
Where SCM Meets Data Science and AI.
Real-world methods for supply chain and operations management professionals who want to go beyond Excel — with reproducible code, realistic datasets, and techniques you can apply today.
Newest Entries
-
Win Without Fighting: The Supreme Art in Business Strategy
Sun Tzu’s most cited principle is also his most misread. Winning without fighting is not pacifism — it is raising the cost of opposition so high that conflict becomes irrational for the adversary.
-
Shaping the Battlefield: Sun Tzu on Positioning Before Competition
Sun Tzu’s most underappreciated concept is shih (势) — the potential energy of a…
-
Know Before You Move: Sun Tzu’s Intelligence Doctrine
Sun Tzu’s Chapter XIII is a 2,500-year-old empirical claim: foreknowledge cannot be deduced from…
AI coding AI strategy ARIMA Art of War bupaR Claude Code context engineering data visualization DDMRP demand-driven demand forecasting demand planning developer tools ETS Excel fable forecast accuracy Forecasting fpp3 ggplot2 inventory inventory management lean LLM machine-learning machine learning manufacturing MRP process-mining procurement prompt engineering pull-system R R programming S&OP seasonality Shiny Strategy That Lasts Sun Tzu supplier negotiation supply-chain supply chain supply chain AI supply chain analytics time series
-
Win Without Fighting: The Supreme Art in Business Strategy
Sun Tzu’s most cited principle is also his most misread. Winning without fighting is not pacifism — it is raising the cost of opposition so high that conflict becomes irrational for the adversary.
-
Shaping the Battlefield: Sun Tzu on Positioning Before Competition
Sun Tzu’s most underappreciated concept is shih (势) — the potential energy of a chosen position. The decisive act in strategy isn’t the fight, it’s the positioning that makes the fight unwinnable for the other side.
-
Know Before You Move: Sun Tzu’s Intelligence Doctrine
Sun Tzu’s Chapter XIII is a 2,500-year-old empirical claim: foreknowledge cannot be deduced from inside the room. Most companies still get this wrong — and the failure rates are measurable.
-
30 Books Every Forecaster, Demand Planner, and S&OP Lead Should Read — The Inphronesys Bookshelf
An interactive 30-book bookshelf for forecasters, demand planners, S&OP leads, supply chain strategists, and the data scientists who keep them honest. Filter by category and level, build a reading list for your role.
-
The Folly of Forecasting
From the Pythia at Delphi to Google’s GraphCast — humans have always demanded the future. Why some forecasts have gotten dramatically better, why others haven’t, and why AI will not deliver the silver bullet.
-
Why VAR Beat Google’s TimesFM — and How to Build One in R
A peer-reviewed 2025 study put Google’s TimesFM foundation model head-to-head with vector autoregression on real hospital data. Spoiler: the 1980s econometric model won. Here’s what VAR is, why it works for supply chain, and how to build one in R.
-
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.
-
The 20 Most Influential People in Forecasting (And What to Learn From Each)
A TIME 100-style guide to the academics, ML engineers, and supply chain voices who shaped modern forecasting — and the one resource to start with for each.
-
When the Algorithm Is Wrong and the Expert Is Right
Statistical models don’t know about your supplier’s factory fire, your competitor’s clearance sale, or the regulation that just changed. Here’s when expert judgment beats the algorithm — and the biases that make it worse.
-
The M5 Lesson: Why Simple Still Beats Fancy in Supply Chain Forecasting
The 2020 M5 competition taught a lesson the forecasting world keeps forgetting: on real supply chain data, simple models win more often than you’d think. Here’s what the Walmart SKU benchmark actually showed — and why it matters for today’s Time Series Foundation Model hype.
-
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.
-
Design for AI: What 40 Years of DFMA Teaches Us About Working With LLMs
Forty years ago, Boothroyd & Dewhurst showed that manufacturing cost was a design problem. Today, bad prompts and failing AI pilots are the same kind of mistake. Here are 7 principles for designing work that LLMs can actually execute.
-
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.
-
Anthropic Just Killed One of Its Own Prompting Tricks — Here’s What That Means
Six years ago prompting was a happy accident inside a GPT-3 paper. Today it’s the single skill separating AI winners from losers. Here’s the complete history — what Anthropic, OpenAI and Google actually published, and what still matters in 2026.