Demand Forecasting in Practice
A 65-minute intermediate course for ops practitioners actually building forecasting — model choice, evaluation methodology, S&OP integration, and the production failure modes.
Last updated: 2026-05-19
What you'll learn
By the end of this course you'll be able to:
- Forecasting theory in 10 minutes — what matters in practice
- Data prep reality — the part that consumes 60% of project time
- Choosing the model — ARIMA, Prophet, ML ensembles, LLM-based
- Evaluation methodology — MAPE, sMAPE, WAPE, and which to trust when
- Integration into the S&OP cadence and continuous retraining
- Common production failures — and how to spot them before customers do
Who this is for
Operations practitioners, demand planners, supply chain analysts, and technical product owners actually responsible for building and running forecasting in production. Especially useful for teams operating across retail, e-commerce, and manufacturing in India, GCC, Africa, and SEA where promotion-driven and Ramadan/festive-cycle volatility breaks naive models.
Prerequisites
- · ai-for-operations-supply-chain
Curriculum
8 chapters · 2 hands-on exercises · capstone challenge
Each chapter ends with the learning objectives ticked off. Quizzes are auto-graded with feedback; exercises are open-ended and produce artifacts you can take to your team.
1. Forecasting theory in 10 minutes
- Distinguish trend, seasonality, level, and exogenous drivers in your series
- Recognize when a forecasting problem is actually a different problem
2. Data prep reality
- Handle stock-outs, promotions, and price-change effects in history
- Build feature stores that don't leak target signal
3. Choosing the model — ARIMA, Prophet, ML ensembles, LLM-based
- Pick the right model class for your data volume, horizon, and SKU count
- Spot the 3 cases where LLM-based forecasting is genuinely the right tool
4. Evaluation methodology — MAPE, sMAPE, WAPE
- Choose the right error metric for intermittent demand and high-volume SKUs
- Design backtests that match the actual forecast cadence
5. Integration into S&OP cadence
- Land the forecast in your monthly S&OP rhythm without breaking it
- Translate forecast confidence into inventory and capacity decisions
6. Continuous retraining
- Decide retrain cadence per SKU class with drift detection
- Avoid the "we trained once and forgot" silent-decay pattern
7. Common production failures
- Recognize the 5 production failures: leakage, drift, promo blindness, regime change, schema breaks
- Build monitoring that surfaces them before the demand planner does
Capstone: Capstone: Your forecasting build plan
- Pick a real SKU subset and design the end-to-end forecasting pipeline
- Define accuracy targets, retrain cadence, and S&OP handoff before code
Capstone deliverable: Every learner who completes this course produces «Your End-to-End Forecasting Build Plan» — a tangible artifact you take back to your organization.
Curriculum live · full chapter content rolling out through 2026.
The outline, learning objectives, references, and capstone deliverable are published. Full chapter content (video, narration, exercises) ships progressively. Get notified when each chapter goes live.
References & sources
Built on cited sources — not vibes.
Every course is researched fresh against vendor documentation, regulatory sources, and peer-reviewed work. Sources used in this course:
MIT Center for Transportation & Logistics — AI in SCM
MIT CTL · Source link
McKinsey — Operations and Supply Chain Insights
McKinsey & Company · Source link
Gartner — Supply Chain Top Trends
Gartner Research · Source link
NIST AI Risk Management Framework
NIST · Source link
Course details
Track
By Function
Level
Intermediate
Audience
Individual contributor, Manager, Director, Technical practitioner
Function
Operations & Supply Chain
Industry
Retail & E-commerce, Manufacturing, Cross-Industry
Stack
Microsoft, Open-source, Stack-agnostic
Paired Gennoor Way phase
innovate, build
Format
video, reading, interactive
You finished the course. Now what?
From course to outcome.
Reading this course is step one. The next step is applying it where you work. Here's how Gennoor helps — without the deck, without the pitch.
Run this for your team
A 2-day workshop or virtual cohort for up to 25 of your people, with exercises run on your data and a 30-day adoption plan.
From $5k · 2 weeks · function-specific
Apply this to your data
A 4–6 week pilot that takes what you learned and ships a working system inside your environment. Fixed scope, fixed price, code transferred day one.
From $25k · 6 weeks · production-grade
Just want to talk?
Free 30-minute call. No deck, no pitch. We listen to your situation and tell you honestly what makes sense — even if it isn't us.
Free · no commitment · 30 minutes
Or just keep learning. We recommend next:
Just finished «Demand Forecasting in Practice». Want this to go further at your organization?