Welcome back to Practical Time Series Analysis, and welcome to week six. Well, you did it. This is the last week of the course, almost there. What we'll be dealing with in this important week is the concept of seasonality. You can see the S in front of that SARIMA expression, Seasonal Auto Regressive Integrated Moving Average models. The idea of seasonality is pretty basic, pretty fundamental, and pretty obvious. There are lots of data sets like weather data, sunspot data, data having to do a tree rings, etc., that exhibit a regular pattern, a repeating pattern, a cyclic pattern, sales data may be like this where things are seasonal. So, the idea of seasonality is important and we bring it into our modeling in a formal model, the SARIMA model this week. We'll also deal with the concept of forecasting and use the technique of exponential smoothing. The basic idea there is that if you wanted to predict what the weather would be like tomorrow, the easiest model imaginable as far as I can see is to say, "well, tomorrow's going to be just like it was today." So we would predict one period into the future just based upon what was happening today in time. This is a pretty poor model and of course, we can do better. We should probably include two days ago, three days ago, five days ago. How far back though would you like to go? There's this idea in doing forecasting that you would like to privilege data points that are closer in time to the event you're trying to forecast and deemphasize those data points that are further away. Your old friend, the geometric series, will come in here, and will show a little bit of the mathematics why this brings you to exponential modeling. So, we deal with a single, double, and triple exponential smoothing and this will allow us to build models that do good forecasts including trend and seasonality. So it's very important week. Have a terrific week.