Improved Navigation Pattern By Association Rule Mining

Balakumar, M., Raji, L., Prabhu, D., Sathishkumar, C., Prabu, P., Mohan, V., & Balasubramanyam, M. (2016).

The competition between retailers is really intense, which force them to improve themselves to avoid a business failure. Data mining is one of the ways that retailers use to help with improvement. The data mining can be done by having a special program that can track the customers’ purchases. Most retailers use the “membership card” method to collect their customers’ data. Every time a customer purchases goods with the card, the system will collect the purchase history for analyzation. Retailers then use the data “to learn what customers want, understand historical trends, and improve the quality of marketing decisions” (Corrigan, Craciun, & Powell, 2014, p. 160). It is important to retailers to understand the demand from both suppliers and customers so that they can have a better marketing strategy in the future.

The method employs data mining techniques such as a frequent pattern and reference mining found from (Holland et al., 2003; KieBling & Kostler, 2002) and (Ivancy & Vajk, 2006). Frequent and reference mining is a heavily research area in data mining with wide range applications for discovering a pattern from Web log data to obtain information about navigational behavior of

Lots of persons interact everyday with web sites around the world. Massive amount of data are being generated and these information could be much respected to the company in the field of accepting Client’s behaviours. Web usage mining is relative independent, but not sequestered category, which mainly describes the techniques that discover the user's usage pattern and try to predict the user's behaviours. Web usage mining is the area of data mining which deals with the novelty and study of usage patterns with use of Web log data. Specifically web logs in direction to advance web based applications.

SUBMITTED BY: JHA PRAVIN KUMAR JOSHI SOURABH MALANI GOVIND 221071 221074 221094 GUIDED BY: Prof. T.K.GANGULI

The key aim of this project is to develop an information system based on data mining techniques to build upon existing customer relationships and increase profit. Part & Parcel Computers has been at the forefront of the computer parts industry for the past fifteen years. They have developed a reputation for the cheapest computer parts by focussing on a cost-leadership strategy. P&P computers have a loyalty card programme that provides discounts and benefits to its customers but has not used this collected data to specifically identify and target its loyal customers. Unless P&P computers build sales volume with the data, it is merely an overhead without any tangible benefit (Cox, 2012).

It is our honor and gives us great pleasure to assist you in setting up and intelligent business system. An intelligent business system is vital for a business with an online presence. This system must be able to process and analyze large amounts of data and communicate with other systems. We have reviewed your request and have compile the requested data in order to suggest viable solutions to help incorporate a e-commerce strategy that will help your company be successful in the current and future markets.

The web is highly dynamic; lots of pages are added, updated and removed everyday and it handle huge set of information hence there is an arrival of many number of problems or issues. Normally, web data is highly dimensional, limited query interfaces, keyword oriented search and limited customization to individual user. Due to this, it is very difficult to find the relevant information from the web which may create new issues. Web mining procedures are classification, clustering and association laws which are used to understand the customer behavior , evaluated a particular website by using traditional data mining parameter. Web mining process is divided into four steps; they are resources finding, data selection and pre-processing, generalization and analysis. Web measurement or web analytics are one of the significant challenged in web mining. The measurement factors are hits, page views, visits or user sessions and find the unique visitor regularly used to measures the user impact of various proposed changes. Large institutions and organizations archived usage data from the web sites. The main problem is that, detecting and/or preventing fraud activities. The web usage mining algorithms are more effective and accurate. But there is a challenge that has to be taken into consideration. Web cleaning is the most significant process but data cleaning becomes difficult when it comes to heterogeneous data. Maintaining accurateness in classifying the

In DM Association rule mining becomes one of the serious tasks of adjective technique which can be defined as discovering important patterns from large collection of data. Mining frequent itemset is very essential component of association rule mining.

Data mining techniques can be mainly divided into three categories: Web structural mining, Web Content mining and web usage mining. Web structural mining is used to discover structure from data available on web like hyperlinks and documents. It can be helpful to the user for navigating within documents as mining can be done to retrieve intra and inter hyperlinks and DOM structure out of documents. Web Content mining can be used to extract information from the data available on web like texts, videos, images, audio files etc. Web usage mining is the application of data mining techniques to discover interesting usage patterns from web usage data, in order to understand and better serve the needs of web-based applications (Srivastava, Cooley, Deshpande, and Tan 2000). Websites or usage data takes user’s available information and browsing history, location of user etc. as input for mining information. Web usage mining can be further divided into three categories depending upon the type of data used for mining: web server logs, application server, application level logs. Web usage mining can be highly helpful in mining the data for web applications and thus helping development in fields like E-Commerce. It can be helpful to discover usage patterns from Web data, thus helping serve better the needs of Web-based applications. Web usage mining can be categorized into three different phases: Preprocessing, Pattern Discovery and Pattern Analysis. I believe, this

As with the development of the IT technologies , the amount of cumulative data is also Growing. It has resulted large amount of data stock in databases therefore the Data mining comes into model to explore and analyses the databases to extract the interesting and previously obscure patterns and rules well-known as association rule mining It was first introduced in 1993.

Abstract— Data mining is logical process that is used to extract or “mining” large amount of data in order to find useful data [2]. Knowledge discovery from Data or KDD is synonym for Data Mining[13].There are many different types of techniques that can be used to retrieve information from large amount of data. Each type of technique will generate different results. The type of data mining technique that should be selected depends on the type of business problem that we are trying to solve.

Although association rule methods have advantages, there are also some limitations that might cause loosing information. Exemplary association rules concentrate on the co-occurrence of items like purchased products, visited web pages, etc. within the transaction set. A single transaction can be a payment for purchased products or services, an order with a set of items with a historical session in a web portal. Alternate independence of items, products and web pages, is one of the most significant hypotheses of the technique, but it is not fulfilled in the web domain. Web pages are linked with each other by using hyperlinks, and they often calibrate all potential navigational paths. A user can enter the required web page address URL to a browser. However, most navigation is completed with the help of hyperlinks created by site administrators. Hence, the web structure sorely incarcerates visited list of pages, user sessions, which are not independent of one another as products in a ideal store. To access a page, the user is usually imposed to

After a study of literature review the concluded that the Association rule with Apriori Algorithm is used in combination of Fuzzy c means clustering and it gives result better Accuracy in web page prediction. Also we use Association rule with Apriori algorithm and Markov model in web page prediction then it may also result a highest probability in web page and helped to predict the user access behavior and also decrease the access time of user. So our new proposed methodology has following methods:

I undersigned ………………………a student of T.Y.B.B.A., here by declare that the project work presented in this report is my own work and has been carried out under the supervision of prof. Kuldeep Jobanputra of R.P.Bhalodia College, Rajkot. This work has not been previously report submitted to any other university for any other examination.