AIExplainer

What is auto-regressive model?

A type of machine learning model that predicts future values based on past values

An auto-regressive model is a statistical model that uses the past values of a time series to forecast future values. It's called 'auto-regressive' because it uses the model's own past predictions to make new predictions.

Think of an auto-regressive model like a person trying to predict the next note in a song. They listen to the previous notes and use that information to guess the next one, rather than just making a random guess.

A company like Netflix might use an auto-regressive model to predict how many users will watch a particular show next week, based on how many users watched it in the past few weeks.

Auto-regressive models are commonly used in finance to predict stock prices, in weather forecasting to predict future temperatures, and in speech recognition to predict the next word in a sentence.

One common misconception is that auto-regressive models can only be used for time series data, but they can also be used for other types of data that have a strong temporal component.

Auto-regressive models have been around since the 1950s, but they've become much more popular in recent years with the rise of machine learning and big data.

AR model autoregressive model time series model

Three products for different needs — explore what’s relevant to you.