• E.Suganya
• Dr.S.Vijayarani
• Ms. V.Eswary

The Web has recently become a powerful stand for retrieval of information and discovering knowledge from web data. The Web mining is one of the applications of data mining techniques to depict the knowledge out of web log data. Web Usage Mining consists as the process of data cleaning, data preprocessing, pattern discovery and pattern analysis. The main aim of this research work is to understand the web usage mining process like preprocessing of web usage data also find session information and their analysis using association rule mining algorithms such as Apriori, FP-Growth and Improved FP-Growth. The real time dataset contains three months information which includes 232 instances and 3 attributes, namely IP address, URL and time taken. Here we transformed the dataset i.e. IP address is considered as transaction id and URL is considered as transaction items and execution time is considered as time taken in seconds. Here the same user visits one or more website so 232 instances are transformed into 110 instances. For example, IP address-1 visits A, B, C URLs. From the observation, based on the performance analysis improved FP Growth algorithm gives better results while comparing other algorithms.

Web Usage Mining, Web Log Analysis, Association Rule Mining, Apriori, FP-Growth

"Web Log Analysis Using Association Rule Mining Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 2, page no.333-342, February-2019, Available :http://www.jetir.org/papers/JETIR1902440.pdf

"Web Log Analysis Using Association Rule Mining Algorithms", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 2, page no. pp333-342, February-2019, Available at : http://www.jetir.org/papers/JETIR1902440.pdf