AI engineering glossary · Time series recsys
What is ARMA?
ARMA (also called Autoregressive moving average): A model combining autoregressive and moving-average parts to describe a stationary series with few parameters. ARMA(p, q) uses p lagged values and q lagged shocks. It needs the series to be stationary, so differencing or transformation is usually applied first, and orders are chosen from correlation plots or information criteria.
ARMA: an example
ARMA(1,1): y_t = c + 0.6*y_(t-1) + e_t + 0.3*e_(t-1).
Related terms
More Time series recsys terms
- Augmented Dickey-Fuller test
- Autocorrelation
- Autocorrelation function
- Backtesting
- Bayesian personalised ranking
- Box-Jenkins method
- Calendar features
- Candidate generation
Where you learn it
ARMA is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.