I have a univariate time series dataset that represents a continuously growing trend, but the slope changes at different intervals. I want to predict future values of this time series.

Here are some key details:

• The series is always increasing.
• The slope changes at various points.
• The data has only one variable.
• I am looking for suitable models or methods to accurately predict future values.
• I need to perform forecasting beyond the test set, meaning using predictions to predict further into the future iteratively.

So far, I have considered linear regression, but it doesn’t handle the changing slopes well. I have also looked into ARIMA, but I’m not sure how to configure it for this scenario.

Can anyone recommend appropriate models or techniques in Python to handle this type of time series? Examples or references to tutorials would be greatly appreciated.