Challenge #24: ARIMA Time Series

[mpennington]

Solution attached.

Spoiler

[SamDesk]

Spoiler

Hey @AYXAcademy, think the solution needs updating as the workflow produces a different output from the stored output values. Probably an update in the R package at some point as caused this.

Sam 🙂

[AngelosPachis]

Challenge #24 solved

[avinashsunchu]

Spoiler

 

[kaianderson]

Here's my solution!

[atcodedog05]

On a spree to binge complete weekly challenges

Third times the charm. I got my numbers to finally match on the third time 🙂

Spoiler

This is my solution

[AndrewS]

#24-same variances on forecasts.

[steven4320555]

As previous predictive analysis exercise, the challenge is good to get an understanding on how to connect the flow to make a general prediction. But the default output is not that convincing. Ideally, everyone should have difference predictions depending on how people model the data, but exercise is exercise 🙂

Spoiler

The default fitted model has a time-lag, and tend to give higher estimations for starts of the year. I would love to estimate something around 100, based on previous two years' data.

I tried to play with the adjustable parameters, but came acorss some errors.

It is easy to build the model, but will take some time to understand how the model work. Will time sometime read the recommended reference material https://otexts.com/fpp2/