Product Recommendation for E-commerce
How "you might also like" works, the data behind it, bundles, and how to measure the impact.
What this track covers
For e-commerce marketers, merchandisers and product managers who are responsible for product recommendations without having to build the model. The three basic approaches, the behaviour and catalogue data they need, the best places for recommendations, market basket analysis (support, confidence, lift), measuring real impact with A/B tests, and the business rules, privacy and labelling of sponsored recommendations. No coding.
New to AI? Every track builds on AI & Data Fundamentals.
What you will be able to do
- Explain popularity, content-based and collaborative filtering recommendations
- Choose the placement and type of recommendation for each page of a store
- Read support, confidence and lift from basket data
- Measure recommendation impact with A/B tests, not click counts
Units and bites
- Unit 14 bitesAbout 12 min
How product recommendations work
Popular, similar and "people like you": the three basic ways to recommend a product.
- 3 min
Three ways to recommend a product
Almost every "you might also like" shelf is built from one of three ideas.
- 3 min
Why recommendations matter
Big catalogue, small screen: recommendations help shoppers find what they weren't searching for.
- 3 min
Blending approaches
How large stores mix popular, similar and personal in one shelf.
- 3 min
Build, buy or use the marketplace
Choosing between a ready-made tool, your own data team, or the built-in features of Shopee and Tokopedia.
- Unit 24 bitesAbout 12 min
The data behind recommendations
Clicks, carts, purchases and catalogue attributes: the fuel of every recommender.
- 3 min
Behaviour events
View, add to cart and buy: signals of different strength.
- 3 min
Implicit and explicit feedback
Star ratings are rare; behaviour is always there. How to read both.
- 3 min
Catalogue data quality
Tidy categories, colours, sizes and brands make similar-product recommendations far better.
- 3 min
The cold start problem
New products and new visitors with no history, and how to handle them.
- Unit 35 bitesAbout 15 min
Where recommendations go
Home page, product page, cart, email, WhatsApp and search.
- 3 min
Home page shelves
Recommendations for visitors who don't know yet what they want.
- 3 min
Similar items on the product page
Alternatives for shoppers who are still comparing.
- 3 min
Cart and checkout cross-sell
Complementary products at the right moment, without getting in the way of payment.
- 3 min
Email and WhatsApp
Recommendations in post-purchase messages and abandoned-cart reminders.
- 3 min
Search and browse
Personalising the order of search results and category pages.
- Unit 44 bitesAbout 12 min
Bundles and cross-sell
Market basket analysis: support, confidence and lift, with simple arithmetic.
- 3 min
Market basket analysis
Finding products that are often bought together from transaction data.
- 3 min
Support and confidence
How often two products are bought together, and how likely one is given the other.
- 3 min
Lift: a link that is really there
Why "everyone buys bottled water" is not a clever recommendation.
- 3 min
Designing bundles
From basket patterns to product bundles and sensible bundle prices.
- Unit 54 bitesAbout 12 min
Measuring recommendations
Clicks on the shelf are not the goal. A/B tests, revenue per visitor and cannibalisation.
- 3 min
Clicks aren't the goal
A shelf that gets lots of clicks doesn't necessarily add sales.
- 3 min
A/B testing recommendations
Comparing visitors who see recommendations with those who do not.
- 3 min
Revenue per visitor and AOV
The metrics that show whether recommendations add basket value.
- 3 min
Cannibalisation
When recommendations only move purchases that would have happened anyway.
- Unit 64 bitesAbout 12 min
Responsible recommendations
Business rules, stock and margin, customer privacy and sponsored recommendations.
- 3 min
Business rules
Don't recommend products that are out of stock, recalled or inappropriate.
- 3 min
Margin vs relevance
Pushing high-margin products without losing the shopper's trust.
- 3 min
Privacy and customer data
Consent, Indonesia's data-protection law, and which data is fair to use for personalisation.
- 3 min
Sponsored recommendations
Ads in the recommendation shelf, and the duty to label them clearly.
Questions about this track
Learning
How long does Product Recommendation for E-commerce take?
About 75 minutes in all: 6 units made of 25 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 Product Recommendation for 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 Retail & E-commerceForecast demand, plan stock, and be ready for Ramadan, 11.11 and 12.12.
- 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 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.
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 read
How to Learn AI From Zero, Without Coding
Yes, you can learn AI without writing any code. To use AI well at work you need four things: a basic idea of how it works, a sense of where it fails, practice with one or two free tools, and the habit of checking every answer before you use it.
8 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