Demand Forecasting for E-commerce
Never overstock or understock.
A practical guide to demand forecasting, safety stock calculation, and replenishment logic for e-commerce. Covers ARIMA, EWMA, and ML-based models with real inventory management patterns.
Inside the guide
What You'll Learn
EWMA Forecasting
Lightweight demand prediction with trend and seasonality decomposition. No ML required.
Safety Stock Calculator
Z-score service level, lead time variability, and demand variability combined into replenishment quantities.
Reorder Point Logic
Dynamic ROP calculation per SKU with automatic review triggers.
ML Upgrade Path
When and how to graduate from EWMA to Prophet, LightGBM, or DeepAR.
Stockout Detection
Real-time stockout signals, phantom inventory patterns, and correction logic.
Table of Contents
Who This Is For
Written by engineers, for engineers
Senior Engineer
Building production systems and tired of re-inventing the wheel on every project.
Software Architect
Needs battle-tested patterns to back architectural decisions with evidence.
Startup CTO
Must ship fast without accumulating technical debt that kills you later.
The Problem
Overstocking ties up capital; understocking kills conversion — most teams do both
Spreadsheet-based forecasting breaks at 500+ SKUs
ML forecasting guides skip the inventory policy layer entirely
Get Instant Access
One-time payment. Instant PDF download.
Personal License
- Guide PDF
- Python code examples
- Spreadsheet calculator included
- Lifetime updates
Frequently Asked Questions
Do I need a data science background?
No. EWMA and safety stock are high-school math. The guide starts there and explains when to upgrade.
Does this cover seasonal products?
Yes. Seasonality decomposition and holiday lift patterns are covered explicitly.