Machine Learning (ML)
TL;DR
A subset of AI in which systems learn from data to improve their performance without being explicitly programmed.
Machine Learning (ML) is a branch of artificial intelligence in which algorithms identify patterns in data and learn to make predictions or decisions without being explicitly programmed for each scenario. Models improve over time as they are exposed to more data — the more they learn, the better they perform.
ML encompasses three core paradigms: supervised learning (learning from labelled training data), unsupervised learning (finding patterns in unlabelled data), and reinforcement learning (learning through reward signals). Deep learning — a subfield of ML using multi-layered neural networks — powers modern AI breakthroughs including LLMs, image generation, and speech recognition.
For businesses, ML applications include predictive maintenance, churn prediction, recommendation engines, fraud detection, dynamic pricing, and personalisation systems. ML engineers typically work with Python (scikit-learn, TensorFlow, PyTorch) and cloud ML platforms from AWS, Google, and Azure.
Examples in Practice
Netflix's recommendation engine, spam email detection, credit card fraud alerts, predictive demand forecasting.