Product recommendations
How "you might also like" works, the data behind it, and how to prove it pays.
What this course covers
For data analysts and data scientists who build or evaluate product recommendations, and for the e-commerce teams who own them. The three basic approaches (popularity, content-based and collaborative filtering), with "often bought together" counts and lift worked out from order data, the behaviour and catalogue data they need, and the cold start problem. Then measuring real impact with A/B tests rather than clicks, business rules and privacy, and building a simple recommender with SQL and Python. The examples come from online shops and marketplaces in Indonesia.
New to AI? Start with AI & data fundamentals.
Part of the career paths:Data scientist
What you will be able to do
- Explain popularity, content-based and collaborative filtering recommendations, and when to use each
- Work out "often bought together" and lift from order data
- Measure recommendation impact with A/B tests, not click counts
- Build a simple recommender with SQL and Python
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
Where an "often bought together" list comes from, and how large stores mix popular, similar and personal in one shelf.
- 3 min
Build, buy or use the marketplace
Choosing between the built-in features of Shopee and Tokopedia, a ready-made tool, or your own data team, and what decides it.
- 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 34 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 44 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.
- Unit 54 bitesAbout 12 min
Building a simple recommender
From an orders table to a recommendation shelf: SQL, Python and testing before launch.
- 3 min
Counting "bought together" in SQL
Self-joining the order items table to count product pairs, then normalising them with lift.
- 3 min
Item similarity in Python
A user × product matrix and cosine similarity with pandas and scikit-learn.
- 3 min
Testing a recommender before launch
Hide the last purchase, then measure how often it shows up in the top of the list (hit rate).
- 3 min
From notebook to shelf
A daily job that recomputes recommendations and stores them in a table the app reads.
Questions about this course
Learning
How long does Product recommendations take?
About 60 minutes in all: 5 units made of 20 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?
Not to start. The foundations explain every idea in plain words first; where a course uses SQL or Python, it teaches it from the beginning, with a playground in the lesson.
Where should I start?
If you are new to AI, begin with AI & data fundamentals. If you know the job you want, follow its career path; Product recommendations has a place in it.
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 courses
- AI & data fundamentalsHow AI works, how to instruct it, and how to read numbers honestly.
- Data analystHow analysts think and work: from a business question to an answer people use.
- Data engineerBuilding pipelines that deliver data on time and correct: SQL, Python, orchestration and warehouses.
- Data scientistWhat data scientists do, and how to use LLMs in the work.
- Data preparationFrom a raw export to a table you can trust: tidy shape, missing values, duplicates and formats.
- Data visualisationCharts that answer a question honestly, from picking the type to dashboards and stories.
- SQL for analysisAsking the database directly: filtering, summarising, joining tables and window functions.
- StatisticsThe statistics every data role uses: summarising, reading distributions and measuring uncertainty.
- Supervised and unsupervised learningThe two ways machines learn from data: with answers, and without them.
- A/B testingMeasuring whether a change really worked, with two random groups and an honestly read result.
- ForecastingForecast demand as a range, ready for Ramadan, 11.11 and 12.12.
- Customer segmentationSplitting customers into groups that differ, then treating each group differently.
- Social media analyticsRead Instagram, TikTok and YouTube numbers honestly, and use AI without being fooled.
- AI for finance reconciliationMatching bank statements to invoices: rules first, AI for the rest, people decide.
- AI for SEOHow search works in the age of AI answers, keyword research, Search Console, and writing with AI responsibly.
Read while you wait
Guides from the Datamew team, free on the web today.
How to Become a Data Analyst in Indonesia: Skills, Roadmap and Salary (2026)
To become a data analyst, learn spreadsheets, SQL, one BI tool such as Looker Studio or Power BI, basic statistics, and how to explain a finding in plain words. Most people can learn the basics in about six months part-time, then need two or three portfolio projects to get interviews. In Indonesia the average data analyst salary on Indeed is about Rp6.3 million a month.
8 min readHow to Become a Data Scientist in Indonesia: Skills, Roadmap and Salary (2026)
A data scientist uses Python, statistics and machine learning to predict what will happen and to test what works. Most people get there through data analysis first: learn SQL and statistics, then Python, experiments and machine learning, which takes roughly a year part-time. In Indonesia, data scientist salaries on Indeed average about Rp14.5 million a month.
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
- Use it now onthe web