InPhroNeSys
Where SCM Meets Data Science and AI.
Real-world methods for procurement, inventory, and operations professionals who want to go beyond Excel — with reproducible code, realistic datasets, and techniques you can apply today.
Newest Entries
-
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…
-
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…
-
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…
agentic coding AI coding ARIMA bupaR Claude Code context engineering cost analysis data quality data visualization DDMRP demand-driven demand forecasting demand planning developer tools ERP ETS Excel forecast accuracy Forecasting fpp3 ggplot2 inventory management LLM machine-learning manufacturing master data MRP open source process-mining procurement prompt engineering prophet pull-system R R programming RStudio seasonality Shiny supplier negotiation supply-chain supply chain AI supply chain analytics tidyverts time series visualization
-
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.
-
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.
-
When S&OP Fails: A Data-Driven Survival Guide for Production Planners
Only 15% of companies run S&OP successfully. For the other 85%, here’s a data-driven toolkit that lets production planners bypass the broken process.
-
Master Claude Code: A Free Interactive Training Program
Nine modules, quizzes, hands-on exercises, and a certificate — all in a single HTML file. A free training program to take you from Claude Code beginner to top 10% user.
-
Prompting Just Split Into 4 Different Skills — Here’s How to Master Each One
Prompt engineering is dead. In its place, four distinct disciplines have emerged — Prompt Craft, Context Engineering, Intent Engineering, and Specification Engineering. This post breaks down the framework, shows where Klarna’s $40M AI bet went wrong, and gives you a concrete path to mastery.
-
The Experience Curve: The Most Powerful Cost Model You’re Probably Not Using
Every time cumulative production doubles, costs fall 20-30%. Here’s how to fit experience curves with R and use them for supplier negotiations, cost forecasting, and strategic sourcing.
-
Mastering Claude Code: From First Launch to 250 PRs a Month
Boris Cherny merges 250+ PRs a month with Claude Code. Here’s every trick — from your first /clear to running 10 parallel sessions — organized by difficulty level.