Analytics for the Internet of Things (IoT)

Using R to forecast time series IoT data

The forecast package contains ARIMA functions in R. You can install it with the following code:

install.packages(“forecast”)

The Arima function has settings for the nonseasonal component of a forecast and the seasonal component (if needed). Each is composed of three numbers that represent the order of the autoregressive part, the degree of differencing to be used, and the order of the moving average part. This is commonly notated as (p,d,q) in R documentation. As with all things in data science, the right place to start is to look at your data, note any unusual trends, and perform some diagnostic statistical analysis to understand what are the appropriate values to use for (p,d,q) for both the nonseasonal ...