Markov chain in SAS for clickstream

[vrushankshah]

I have a dataset which contains various clicks which a user did while going through the website. It also contains uniqueid of each user, date and time of the click and their name. Essentially my main aim is to predict what will be next click of the user. For example, if it starts from home then goes to clothing then goes to Denim then from Denim what is the highest probability of its next click?There are 50000 unique click patterns in a month which a user has clicked. Will Markov chain be feasible for such data?

Clicks                                                            Time                                  Id
Home,Clothing,Men,Denim,Home         02/10/2018/3:22pm               1234
Home,Kitchenware,glass,purchase       03/10/2018/4:00pm                4567
Home,Clothing,Men,Denim,Purchase   04/10/2018/3:55pm                7891
Home,Clothing,Men                               05/10/2018/2:56pm                6789

[Ksharp]

It is more like Market Basket Analysis.Change your data like:

Home,Clothing,Men,Denim,Home  1234

-->

Home,Clothing, 1234

Clothing ,Men, 1234

Men,Denim, 1234

Denim,Home  1234

After that count the frequency.

If MC could apply to it , calling @Rick_SAS