Forecasting for Retail & E-commerce
Forecast demand, plan stock, and be ready for Ramadan, 11.11 and 12.12.
What this track covers
For merchandisers, category managers, marketplace sellers and store operators who order stock from an estimate. How to read sales history (which is not the same as demand), seasonal patterns such as Ramadan and Lebaran that move every year, double-date campaigns, forecasting methods a spreadsheet can do, how to measure accuracy, and how to turn a forecast into safety stock and an ordering plan. No coding.
New to AI? Every track builds on AI & Data Fundamentals.
What you will be able to do
- Read sales history and separate trend, seasonality and promotions
- Build a simple forecast as a range, not a single number
- Measure forecast accuracy and bias correctly
- Turn a forecast into safety stock and a reorder point
Units and bites
- Unit 14 bitesAbout 12 min
Forecasting basics
What a forecast is, why it is always wrong, and why that's fine.
- 3 min
A forecast is a range, not a number
Why "we will sell 500 next week" is less useful than "between 420 and 580".
- 3 min
Horizon and granularity
Tomorrow's forecast per SKU is a different job from next quarter's per category, and you need both.
- 3 min
What a forecast is for
Buying, warehouse stock, store staffing and promo budgets each need a different forecast.
- 3 min
A forecast isn't a target
A forecast guesses what will happen; a target is what you want. Mixing them ruins both.
- Unit 25 bitesAbout 15 min
Reading your sales history
Sales data isn't demand data. Cleaning it before it becomes a forecast.
- 3 min
Sales aren't demand
When stock runs out, zero sales does not mean nobody wanted to buy.
- 3 min
Trend, seasonality and noise
The three parts in almost every sales chart, and how to see them.
- 3 min
Promos and outliers
Flagging promo weeks and one-off events so they are not mistaken for a pattern.
- 3 min
SKU, store and channel
When a forecast per SKU per store makes sense, and when to add things up first.
- 3 min
Marketplace data
Reading Shopee, Tokopedia, TikTok Shop and Lazada sales reports as one picture.
- Unit 35 bitesAbout 15 min
Seasonality and events
Ramadan, Lebaran, 11.11, 12.12, payday and school holidays: patterns you can plan for.
- 3 min
Weekly and payday patterns
Why weekends and payday often move daily sales.
- 3 min
Ramadan and Lebaran
Indonesia's biggest season moves about 11 days earlier every year, so the forecast has to move with it.
- 3 min
Double-date campaigns
9.9, 11.11 and 12.12 (Harbolnas): big spikes that often borrow sales from the weeks after.
- 3 min
Holidays and the school calendar
Christmas, Lunar New Year, the new school year and long weekends as markers on the forecast calendar.
- 3 min
Building an events calendar
One table of promo and event dates that makes every later forecast better.
- Unit 45 bitesAbout 15 min
Simple forecasting methods
Methods a spreadsheet can do, and when an AI tool is worth it.
- 3 min
The naive forecast: your benchmark
"Same as last week" or "same as last year": the method every other one has to beat.
- 3 min
Moving averages
Smoothing out noise with the average of the last few weeks, and the price you pay for it.
- 3 min
Seasonal forecasts
Combining the recent trend with last year's seasonal pattern.
- 3 min
Exponential smoothing, without the maths
Giving recent weeks more weight: the idea behind many forecasting tools.
- 3 min
When to use AI forecasting
Machine learning helps with many SKUs and many drivers, not as a substitute for clean data.
- Unit 54 bitesAbout 12 min
Measuring forecast accuracy
Error, bias and MAPE: how to tell whether your forecast is getting better.
- 3 min
Forecast error
The gap between forecast and sales, and why you average it without the plus and minus signs.
- 3 min
MAPE and its traps
The popular percentage error, and why it misleads for slow-moving products.
- 3 min
Bias: always too high or too low
An error that leans one way costs more than a random one.
- 3 min
Is your forecast adding value?
Comparing every method and every manual adjustment with the naive forecast.
- Unit 65 bitesAbout 15 min
From forecast to stock decisions
Safety stock, reorder points, new products and the planning meeting.
- 3 min
Safety stock
Buffer stock for the uncertainty, and the cost of holding too much or too little.
- 3 min
Reorder points
When to order, based on the forecast and the supplier's lead time.
- 3 min
Planning stock for a campaign
Stock for a flash sale or marketplace campaign without a pile of leftovers afterwards.
- 3 min
New products without history
Borrowing the pattern of similar products when there are no sales yet.
- 3 min
The planning meeting
Bringing the forecast, the promo plan and warehouse capacity together into one agreed number.
Questions about this track
Learning
How long does Forecasting for Retail & E-commerce take?
About 84 minutes in all: 6 units made of 28 bites of about three minutes each, and every bite ends with a quick check. You can do one bite a day or several in a row.
Do I need to know how to code?
No. Every Datamew track is written for working professionals without a technical background. Where there is arithmetic, it is the kind you can do on a phone or in a spreadsheet.
Where should I start?
Everyone begins with AI & Data Fundamentals, which covers how AI works, how to write a good prompt and how to read data honestly. Then take Forecasting for Retail & E-commerce for your role.
When can I start learning?
Datamew is coming to iOS and Android soon. There is no release date or price announced yet: join the waitlist and we will tell you when the app is out.
Is it available in Bahasa Indonesia?
Yes. Datamew is written in English and Bahasa Indonesia.
More tracks
- AI & Data FundamentalsHow AI works, how to instruct it, and how to read numbers honestly.
- AI for MarketingResearch, content, personalisation and campaign analysis with AI — with your judgement still in charge.
- Data Analytics for MarketingMetrics, funnels, A/B tests, attribution and cohorts — the numbers behind marketing decisions.
- Data Analytics for HRPeople analytics: turnover, hiring, engagement and pay fairness — with privacy protected.
- Forecasting for MarketingForecast traffic, leads and campaign results, and defend the numbers in the budget meeting.
- Forecasting for FinanceBudgets, revenue and cash forecasts, rolling forecasts and scenarios, with spreadsheet arithmetic.
- Product Recommendation for E-commerceHow "you might also like" works, the data behind it, bundles, and how to measure the impact.
- Product Recommendation for Retail & MediaLoyalty programmes, personal vouchers and "watch next": recommendations beyond the online shop.
Read while you wait
Guides from the Datamew team, free on the web today.
AI Engineer Career Path: Roles, Skills, Salary and a Realistic Roadmap (2026)
An AI engineer builds products on top of existing AI models, such as ChatGPT-style chatbots, document search and AI agents. Most do not train models from scratch. Instead, they connect models to data, tools and users, then test that the results are reliable.
9 min read
How to Write a Good Prompt: A 5-Part Framework for Work
A good prompt gives the AI five things: context, task, input, format and limits. It says who the work is for, what to do, which material to use, how the answer should look and what to avoid. Then you check the answer and ask a follow-up.
7 min readBe first on the app
Leave your email and we will tell you the day Datamew lands on your phone. One email at launch, no spam.
- Coming soon onApp Store
- Coming soon onGoogle Play
- Use it now onthe web