I would like to do sales prediction based on my sales data for a particular product for a year. I understand this is non-stationary data which needs to be converted into stationary data and modeled using auto.arima()
to do forecasting for the next 30 days. I would appreciate if anyone can help me on this using R as I am new to this domain.
Date Code Sales
2015-01-01 65323 2
2015-01-02 65323 1
2015-01-03 65323 3
2015-01-04 65323 3
2015-01-05 65323 2
2015-10-05 65323 1
2015-10-06 65323 1
2015-10-11 65323 1
2015-10-14 65323 1
2015-10-17 65323 2
2015-10-18 65323 1
2015-10-21 65323 1
2015-10-24 65323 1
2015-10-25 65323 2
2015-10-26 65323 1
2015-10-28 65323 1
2015-10-31 65323 2
2015-11-02 65323 1
2015-11-03 65323 1
2015-11-05 65323 1
2015-11-06 65323 1
2015-11-07 65323 1
2015-11-10 65323 2
2015-11-14 65323 3
2015-11-16 65323 1
2015-11-17 65323 1
2015-11-18 65323 1
2015-11-22 65323 3
2015-11-23 65323 3
2015-11-26 65323 3
2015-11-27 65323 2
2015-11-29 65323 4
Best Answer
Try to re-edit data into a doable way. You can manually type them in CSV file. Once you do it, use R studio to read the data and do the following (you can even copy and paste):
Note this is growth rate of sales. to get predicted sales figure, you need convert back.