Are statistical models(like ARIMA, SARIMA) ML-->Supersived Learning model?

Models such as ARIMA SARIMA used in time series forecasting. Which is the AI technique. I can’t put it schematically in my mind. Is there such an answer?
“Forecasting time series is like AI–>ML–>Supervised Learning–>Regression”

I see that ARIMA SARIMA is not a machine learning model, it is a separate statistical model. I’m mixing it up. What is the correct answer?

1 Like

While machine learning models (like certain types of neural networks) can be used for time series forecasting, ARIMA and SARIMA are rooted more in classical statistical analysis rather than in the machine learning subset of AI.



In short: No.

From ChatGPT:

In contrast to traditional machine learning models like neural networks or decision trees, ARIMA and SARIMA rely on statistical methods and do not involve learning from data through optimization algorithms like gradient descent. Instead, they use mathematical equations to model the underlying patterns in the time series data.

So, while ARIMA and SARIMA are important tools in the data scientist’s toolkit, they are not machine learning models in the strictest sense.


Many thanks for the answers. Appreciated

1 Like

Pleast do not come on the forums and quote a chatbot as though it was facts or truth.