From the course: Python for Time Series Forecasting
Join today to access over 24,800 courses taught by industry experts.
SARIMA vs. exponential smoothing - Python Tutorial
From the course: Python for Time Series Forecasting
SARIMA vs. exponential smoothing
- [Instructor] Smoothing models for time series forecasting. In this notebook, you will learn how to develop a new type of model for time series, which is the exponential smoothing. As you can see in the plots, if we visualize it along with the historical values, there is a growing trend that can be captured better by the exponential smoothing than the SARIMA model we covered on previous lessons. In this case, the exponential smoothing is more conservative, as the growth on the trend is not moving up as much as the SARIMA. And this could indicate a better model. Not only we will compare these two models, but also the different configurations that can be applied to this type of models because we will play with the seasonal and trend components, whether they are additive or multiplicative, And the seasonal periods, which in this case will be 12 for these dataset. And after comparing the different configurations, we will understand why the chosen one is the most appropriate. Without…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.