Web usage mining is a way of identifying and analyzing how users interact with a web site. This browsing data collected as web log, which is first preprocessed and then number of data mining methods such as classification, clustering and association rule mining etc. applied to find out interesting patterns. User's demographic information plays important role in designing business strategies, advertisement etc. Previous research shows some techniques to predict these demographic attributes (age gender etc.). This paper discusses detailed review of various preprocessing, prediction and recommendation techniques. © 2017 IEEE.