AI Glossary Models and how they work

Machine learning

MLnoun · pronounced "em-el"

  • Tidio Agents team
  • Updated November 19, 2026
  • 6 min read
  • 6 sources
Definition

Machine learning (ML) is a branch of artificial intelligence in which software learns patterns from examples, instead of following rules a programmer wrote, and uses them to make predictions or decisions about new cases. Tom Mitchell's classic textbook calls it the study of algorithms that improve automatically through experience.1

The practical shift is in who writes the logic. With rules, a person decides that a message containing "refund" goes to billing. With machine learning, the system studies thousands of past messages and the queues they ended up in, and works out its own way to route the next one. That handles the variety of real customer language far better, but it moves the hard work to data: the model can only be as good as the examples it learned from.

Almost every AI system a company buys today is machine learning underneath, from fraud scores to large language models.

Example

Routing a message with rules and with machine learning

An insurer receives a message from a customer. The goal is to send it to the right team on the first try.

Rules

Keywords
CustomerSomeone reversed into my car in a parking lot yesterday. What do I do now, and will my premium go up?
  1. MatchFinds "premium" in the message. Rule: premium questions go to policy sales.
  2. RouteSends the message to the sales queue.
  3. RerouteA sales agent reads it, sees a new claim, and forwards it to claims the next day.

Right words, wrong team. The rule saw a keyword, not the request.

Machine learning

Learned
CustomerSomeone reversed into my car in a parking lot yesterday. What do I do now, and will my premium go up?
  1. Learned fromA classifier trained on past messages labeled with the team that finally resolved them.
  2. PredictMotor claim, first notice of loss. Secondary topic: premium impact.
  3. RouteSends it to motor claims, with the premium question flagged for the reply.

Routed on meaning. The model recognized a pattern it had seen many times.

Illustrative example. A real classifier also returns a confidence score, and low-confidence messages go to a person.

How it works

How machine learning works

A machine learning model is a mathematical function with adjustable parameters. Training shows it many examples, measures how wrong its outputs are, and adjusts the parameters to be less wrong. After training, the parameters are fixed and the model is used on new cases, a step called inference.

Past dataTrainModelPredictMeasureaccuracy drops: retraintickets · transactions · clicks · documents
Training is not a one-off. Customer behavior changes, and a model trained on last year's data slowly gets worse.

Supervised learning

Learns from labeled examples: messages with their correct team, transactions marked as fraud or not. Most business ML is this kind.

Unsupervised learning

Finds structure in unlabeled data, such as clusters of similar complaints nobody had named yet.

Reinforcement learning

Learns by trial and reward. It is used to tune language models toward answers people prefer.

Self-supervised learning

Creates its own labels from raw data, for example by hiding the next word and predicting it. This is how LLMs are pretrained.

Where it fits

Where machine learning sits in AI

The terms nest inside each other. Each level below is a subset of the one above it.

1

Artificial intelligence

Any system that performs tasks associated with intelligence

Includes hand-written rule systems and decision trees as well as learned models.

2

Machine learningThis page

Systems that learn from data

Fraud scores, churn prediction, demand forecasts, recommendation, intent classification.

3

Deep learning

ML with many-layered neural networks

Speech recognition, image recognition, and the models behind modern language understanding.

4

Generative AI and LLMs

Deep learning models that create content

Generative AI: text, images, and code. The engine inside chat assistants and AI agents.

Compared

Machine learning and neighboring approaches

ApproachWhere the logic comes fromGood forWeak at
Rules and RPAPeople write itStable, well-defined processesVariety and messy language
Classic machine learningLearned from labeled dataScoring, ranking, forecasting on structured dataOpen-ended language and writing
Deep learningLearned from large data, layeredSpeech, images, language understandingExplaining its decisions
Generative AIPretrained on broad data, then promptedWriting, summarizing, conversationExact numbers and guaranteed consistency
In practice

Machine learning behind customer-facing AI

Inside a modern AI agent, classic ML models often do the scoring and ranking while a language model does the talking.

Customer support

Intent and priority

Classify each message by intent, language, and urgency so the agent or the right team picks it up first.

message → classify → route
Proactive service

Predict who will leave

A telecom scores customers by churn risk, and an agent contacts the high-risk ones with a relevant offer.

usage data → churn score → outreach
Shopping

Rank the catalog

Learned ranking decides which products appear first for a query, based on what similar shoppers bought.

query → rank → show
Fintech

Flag risky payments

Fraud models score each transaction in real time; the agent explains a blocked payment and verifies the customer.

transaction → risk score → hold or pass
Back office

Match and reconcile

Learned matching pairs invoices with orders and receipts when references are missing or misspelled.

invoice → match → post or flag
Lead generation

Score inbound leads

Predicts which inquiries are likely to buy, so the agent qualifies those first and books them with sales.

inquiry → score → qualify
Risks

Machine learning risks and controls

Bad or biased data

ControlA model learns whatever its data contains, including old mistakes and skews against customer groups. Audit labels and test results by segment before launch.

Drift

ControlCustomer behavior, products, and fraud patterns change, and accuracy falls without warning. Monitor live accuracy and retrain on recent data.5

Hidden maintenance cost

ControlResearchers at Google described the large ongoing maintenance costs of real-world ML systems as technical debt.4 Budget for monitoring, data pipelines, and retraining, not only the first model.

Opaque decisions

ControlSome models cannot explain a single prediction well. Where a decision affects a customer's money or access, log the inputs and keep a person able to review and overturn it.

FAQ

Common questions

What is the difference between AI and machine learning?

AI is the broad goal of building systems that perform tasks associated with intelligence. Machine learning is the most common way to get there today: learning the behavior from data instead of programming it by hand.

Is ChatGPT machine learning?

Yes. It runs on large language models, which are deep learning models trained with self-supervised learning on text and then tuned with human feedback.

What is the difference between machine learning and deep learning?

Deep learning is a subset of machine learning that uses neural networks with many layers. It needs more data and compute, and it handles speech, images, and language far better than earlier methods.

How much data does a machine learning model need?

It depends on the task. Narrow tasks with a few clear categories need far less data than open-ended ones. Starting from a pretrained language model usually reduces the number of labeled examples needed.

Sources

References

  1. Mitchell, T. Machine Learning. McGraw Hill, 1997.
  2. LeCun, Y., Bengio, Y. and Hinton, G. Deep learning. Nature 521 (2015): 436-444.
  3. Zinkevich, M. Rules of Machine Learning: Best Practices for ML Engineering. Google for Developers.
  4. Sculley, D. et al. Hidden Technical Debt in Machine Learning Systems. NeurIPS 2015.
  5. Lu, J. et al. Learning under Concept Drift: A Review. 2020.
  6. European Commission. AI Act, Article 3: Definitions. Regulation (EU) 2024/1689.

Tidio Agents

Build an agent that resolves, not only answers

We design and build custom AI agents for customer service, shopping and back-office work, on your infrastructure, with the code handed over to you. Projects start with a 21-day private AI audit.

Request a call