time series - User Modeling and Anomaly Detection [R] -


i have historical data of online shopping website like;

userid        date        timeonsite   isanomaly?    123   01/01/2012 12:38      14          1     548   01/01/2012 19:56      12          0 

its millions of rows , growing everyday too. using r , mssql.

trying create ml model every users behaviour according timeonsite value. , predict "is next value anomaly/outlier?"

planned logistic regression use. need incremental/online learning model re-train users models every week or month. can't use of historical data every training session.

is there package this? regression not red line, open other methods "ts, svm, knn etc."


Comments

Popular posts from this blog

Sort a complex associative array in PHP -

vb.net - How to ignore if a cell is empty nothing -

recursion - Can every recursive algorithm be improved with dynamic programming? -