Company or project name

No response

Use case

basic minimum use cases:

• calculate Dickey Fuller stat test
• calculate autocorrelation and partial autocorrelation function's
• estimate SARIMAX forecast (or AutoSARIMAX)
• calculate Diebold Mariano stat test

Describe the solution you'd like

ClickHouse's aggregation functions already support linear/logistic regression, their stochastic versions, and some statistical tests. However, this is not enough for frequent scenarios of building predictive models, which is why we have to build ETL processes. To improve performance, it would be beneficial to move the implementation of at least one complete use case directly into the DBMS (like ELT)

Describe alternatives you've considered

No response

Additional context

What do you think about this ? I'm ready to contribute this feature