Think Build Implement Repeat
London, UK +44 7367 067226
WhatsApp FOLLOW f in X
  1. Home
  2. Blog
  3. Explaining an Individual Decision to a Customer
AI & Machine Learning

Explaining an Individual Decision to a Customer

Global explanations do not help someone who was declined. What a per-decision explanation needs to contain, and how to give one without exposing the model.

Updated 2 min readBy SpiderHunts Technologies

Free estimateNo obligation

Get a free estimate

Tell us what you need. A senior engineer reads every enquiry.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →

Quick answer — TL;DR

A customer affected by an automated decision needs to know the main reasons, what would change the outcome and how to challenge it. That is different from explaining how the model works, and it needs designing before launch rather than after the first complaint.

Two different questions

Explainability usually gets discussed as understanding a model overall - which features matter most, how it behaves in general. That is a question for the people who own it.

The person declined, flagged or charged more has a different question: why me, and what can I do about it? Global feature importance does not answer that, and reading it out would be worse than saying nothing.

What an individual explanation should contain

  1. The main factors in this specific case, in plain language, ordered by influence.
  2. What would have to change for a different outcome, where that is actionable.
  3. Whether a person was involved, and how to ask for one.
  4. How to correct the underlying data if it is wrong.
  5. Who to contact, and what happens next.

That fourth point matters more than it gets credit for. A meaningful share of adverse automated decisions trace to incorrect data rather than a wrong model, and a correction route resolves those without anyone appealing.

Language that helps rather than deflects

UnhelpfulBetter
Your application scored below our thresholdThe main factors were a short account history and two recent missed payments
Our system made this decisionThis was decided automatically. You can ask for a human review
We cannot disclose our modelWe can tell you the main reasons and how to have them reviewed
Improve your creditworthinessA longer payment history with us would change this - we can review again in six months

The right-hand column is not more revealing about the model. It is simply more useful to the person reading it.

Without giving away the model

There is a genuine tension where explanation enables gaming - fraud and abuse detection in particular. It is narrower than it is usually claimed to be.

Practical approach: give reasons at the level of broad factors rather than exact thresholds, avoid stating how much a change would move the score, and be more conservative for decisions where gaming carries real cost. For most business decisions - a declined credit limit, a flagged claim - the risk is modest and the obligation is real.

Where you genuinely cannot explain without enabling abuse, that is an argument for a human in the loop, not for an unexplained automated decision.

Design it before you need it

Explanation capability has to be built in. Recovering why a decision was made six months ago requires the inputs, the model version and the score to have been stored at the time.

Retro-fitting that is difficult and sometimes impossible. Storing the explanation alongside the decision, at the moment it is made, is far cheaper than reconstructing it later under pressure. Our note on explainable AI covers the technical side.

If you cannot say why, you are not ready to decide automatically.

FAQ

Frequently asked questions

The questions readers ask us after this guide.

Still have a question?

Ask us directly — a senior engineer will get back to you.

Ask about your project

Are we legally required to explain?

It depends on your jurisdiction and the decision's effect on the person. Where decisions are significant and automated, obligations commonly apply - take specific advice for your situation.

Does explanation require a simple model?

Not necessarily. Per-prediction explanation techniques work with complex models, though simpler models make the explanation easier to state and defend.

How much detail is too much?

Enough for the person to understand and act, without publishing exact thresholds. Broad factors rather than precise weights is usually the right level.

What if the explanation reveals a data error?

That is a good outcome. Correcting it and re-deciding is cheaper than an appeal, and it improves the data for everyone.

Keep reading

More on AI & Machine Learning

Start here

Want machine learning project details from us?

Tell us what you are trying to predict and roughly what data you hold. We will come back with an honest view on whether machine learning is the right tool, what the work would involve and a realistic cost range. If a spreadsheet would do the job, we will say so.

  1. You tell us what you needTwo minutes on the form, or a message on WhatsApp.
  2. A senior engineer reviews itAnd comes back with questions, a realistic range and an honest view on fit.
  3. Free 30-minute scoping callWe talk through scope, options and a realistic estimate — with no obligation.
Free estimateNo obligation

Talk to someone who builds this

Send a short brief and we will come back with an honest view and a realistic range.

Takes under a minute. We never share your details.

  • Free consultation
  • No commitment
  • NDA on request

Prefer to talk? Book a free 30-minute call →