Neural Networks

Australian Electricity Predictions with Neural Networks

You can also embed plots, for example: First, I divided the set into a training and test set, with 20% of the observations held out.

library(dplyr)
electric<-aus_production %>%
  select(c('Quarter', 'Electricity'))

training<-electric[1:174,]
test<-electric[175:218, ]

Models and Prediction

Then I used the NNETAR() function to produce a prediction and tested it, looking at RMSE, etc.

elecmod_2 <-  training %>% 
  model(NNETAR(sqrt(Electricity)))
pred<-forecast(elecmod_2, h=20)
autoplot(pred, training)

library(kableExtra)

## 
## Attaching package: 'kableExtra'

## The following object is masked from 'package:dplyr':
## 
##     group_rows

acc1=accuracy(pred, test)
acc1%>%kbl(caption="Neural Net")%>%kable_classic(html_font="Cambria")

Neural Net

.model	.type	ME	RMSE	MAE	MPE	MAPE	MASE	RMSSE	ACF1
NNETAR(sqrt(Electricity))	Test	1685.941	1972.243	1685.941	3.210316	3.210316	NaN	NaN	0.3063724

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.