ARIMA

Time series model

ARIMA stands for autoregressive integrated moving average, a statistical model used for analyzing and forecasting time series data.

It combines three components: autoregression, differencing to achieve stationarity, and moving average smoothing.

The analyst built an ARIMA model to predict quarterly sales.

Widely used in economics, finance, and weather forecasting. (Capitalized Arima is a city in Trinidad.)

statistical

integrated

Combined into a whole

white noise · parameters · estimation · likelihood · coefficients · variance · random walk

forecasting

time series

Chronologically ordered observations

trend · seasonality · projection · extrapolation · sales forecasting · stock prediction · weather modeling · economic outlook · horizon · residuals

software

R

Eighteenth alphabet symbol

  • PythonLarge nonvenomous squeezer
  • ExcelMicrosoft's data-crunching application
  • SPSSSocial science analytics program

SAS · MATLAB · pandas · implementation · library · function · output · summary · plot

modeling

BIC

Financial institution identifier

seasonal · exogenous · specification · identification · validation · cross-validation · training set · hyperparameter

Categories
Opposites
modeling approach

ARIMAneural network

Interconnected computational nodes mimicking cognition

deep learning · neural networks · machine learning

complexity and structure

ARIMAVAR

Remote match officiating

data structure approach

ARIMAANOVA

Compares means among groups

Phrases
Family

average

Familiarity
Top 2,000,000
Profile
Used worldwide · Timeless · Abstract · Rated G