wsyy
asked on
What to consider when developing a user browsing model?
Hi,
I would like to develop a model to predict the browsing behavior of an Internet user.
The model should possess two features:
1. Can self learn when new data is available.
2. Can respond immediately.
Any thoughts are appreciated!
I would like to develop a model to predict the browsing behavior of an Internet user.
The model should possess two features:
1. Can self learn when new data is available.
2. Can respond immediately.
Any thoughts are appreciated!
ASKER CERTIFIED SOLUTION
membership
This solution is only available to members.
To access this solution, you must be a member of Experts Exchange.
Do you want to predict the next URL to be visited based on past URL visits?
Such a model obviously leaves out many factors that influence a users behaviour,
but there may still be situations when reliable predictions may be possible,
such as a visit to an intro screen that directs to a unique next screen,
but I'm not sure how useful such predictions would be to you.
What data is available to the model, and by what criterion would you consider a model to be a good model?