Predictive Analytics
Using historical data to estimate what will happen next: which customers will lapse, which stock will run out. Useful precisely to the degree that the past resembles the future.
Related terms
Temperature
A setting that controls how predictable an AI’s output is. Low temperature gives safe, repeatable answers; high temperature gives varied, more surprising ones — useful for ideas, risky for facts.
Transformer
The model architecture behind almost every modern AI system, introduced in 2017. Its trick is paying attention to how every word in a passage relates to every other, which is what made fluent machine writing possible.
Recommendation Engine
A system that suggests what somebody might want next based on behaviour — the “customers also bought” of an online shop. One of the oldest commercial uses of machine learning.
AI Agent
An AI that does things rather than only answering — browsing a site, filling a form, completing a booking. It is why websites are starting to be judged on whether a machine can use them, not only read them.
Speakable Schema
Markup identifying the parts of a page suitable to be read aloud by a voice assistant. Narrow in application, but it removes the guesswork about which sentence answers the question.
JSON-LD
The format Google and the AI assistants prefer for structured data — a block of machine-readable facts tucked into the page. It states plainly what prose only implies: this is the business, this is the address, this is the price.