Automation and AI

Machine Learning

Also called ML

The practice of building systems that improve by finding patterns in data instead of following rules written by a person.

Quick facts: Machine Learning

Category
Automation and AI
Also called
ML
Level
Beginner
Affects
Automated bidding, audience targeting, forecasting, personalisation
Where to see it
Google Ads Smart Bidding, GA4 predictive audiences, Meta Advantage+
In this article4
  1. How machine learning works
  2. Why machine learning matters
  3. Common mistakes with machine learning
  4. How to act on it

How machine learning works

A person writing software has to state the rule: if the enquiry mentions a refund, send it to the accounts inbox. Machine learning inverts that. You supply examples of enquiries and where each one ended up, and the system works out the rule itself by finding what the accounts-bound ones have in common. The result is a model — a set of internal settings that turn an input into a prediction.

Two things decide whether it works: the examples and the feedback. If the examples are few, stale, or all of one type, the model learns something narrow and applies it everywhere. If the feedback is wrong — a conversion counted twice, a lead marked good when it never answered the phone — the model learns the wrong lesson faithfully. Nothing in the method corrects for bad input, and no amount of clever tuning makes up for it.

Why machine learning matters

It is already deciding a large part of your marketing whether you engage with it or not. Automated bidding predicts the value of each auction. Audience expansion predicts who resembles your buyers. Email tools predict send times. Recommendation blocks predict the next product. In each case you are no longer setting the rule; you are supplying the training signal.

That changes the job. The highest-leverage work becomes clean, honest data — accurate conversion tracking and analytics, sensible conversion values, and offline outcomes fed back in so the system learns which leads actually became customers rather than which forms got filled in.

Common mistakes with machine learning

Starving it is the most common. These systems need a steady flow of examples, and a small local advertiser in a market like Nepal generates far fewer conversions than the same business would in a larger one. Splitting a modest budget across many narrow campaigns leaves each of them with too little to learn from, and every one sits in a permanent learning phase.

Changing things constantly is the second. Each significant edit resets what the system has worked out, so an account that is adjusted every few days never gets past the guessing stage. The third is assuming a model that worked last season still works now. Prices, competitors and demand shift, the world stops matching the training data, and accuracy quietly decays.

How to act on it

Fix measurement before automation. Decide what a valuable outcome actually is, count it once, give it a value that reflects real margin, and send back what happened after the lead arrived. Then consolidate: fewer campaigns, each with enough volume to learn from, beats a tidy structure that nothing can learn from.

Once it is running, change deliberately and leave time between changes to judge the effect. Review the inputs on a schedule rather than waiting for results to slip, and be willing to retrain or rebuild when the market has moved. Treat the model as a colleague who learns only from what you show them.

Do and do not

Do

  • Clean up conversion tracking before trusting any automation
  • Consolidate budget so each campaign has enough to learn from
  • Feed back which leads actually became customers

Do not

  • Change bidding, budgets and structure all in one week
  • Count the same conversion twice or value every lead equally
  • Assume a model that worked last season still fits today

Questions people ask about this

How much data does machine learning need to be useful?

There is no single threshold, and it depends on how varied the outcomes are and how the platform is set up. The practical test is whether the system's predictions get steadier over time or keep swinging. If they keep swinging, it is being asked to learn from too little, and consolidating budget or counting an earlier step as the conversion usually helps more than tuning settings.

Is machine learning the same thing as AI?

Machine learning is one approach within artificial intelligence, and it is the approach behind almost every AI product a marketer uses. Artificial intelligence is the broader idea of software doing work that once needed human judgement, which historically also included hand-written rule systems. When someone in marketing says AI today, they almost always mean a machine learning model of some kind.

Why did my automated campaign perform worse after I changed it?

Significant edits — new bidding strategy, changed conversion goal, large budget swings, restructured ad groups — disturb what the system has already learned, and it goes back to exploring before it settles. Performance during that period is not a fair read on the change. Make one meaningful change at a time, then let it run long enough to judge properly before touching it again.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.