《an attempt to modeling rule base real time web funnel structure.》由会员分享，可在线阅读，更多相关《an attempt to modeling rule base real time web funnel structure.（12页珍藏版）》请在金锄头文库上搜索。
1、Journal of Business and Retail Management Research (JBRMR) Vol 5 Issue 2 April 2011An attempt to modeling rule base real time web funnel structure Sasadhar BeraShailesh J. Mehta School of Management, Indian Institute of Technology, Mumbai, INDIAPrasun DasSQC & OR Division, Indian Statistical Institu
2、te, Kolkata, INDIAKeywordsE-Commerce, Chat Conversion Funnel, Hot Lead, AOV, Cart Load, AgentAbstract Every retail web site is actively seeking out new innovations and approaches that create competitive advantage and increase the profitability. In general, retailers constantly monitor the behaviour
3、of the real shoppers on the website and any changes in the market requirements. This paper presents a chat invitation web funnel structure, profiling web visitors and selection of hot leads for retail business processes through scoring method using geographic region, product page and other factors.
4、Choosing the right hot prospects through rule base real time chat invitation method based on product type, time on page, cart load, search behavior, cookie information etc. and providing chat to those hot prospects is a special merit to this work. Active rules selection process is done using rule ef
5、fectiveness indicator and chat load contribution which ensures sales revenue, chat volume and profit margin. An indirect increase in customer delight for interacting with representatives is also expected.Introduction The objective of an online shopping is to provide the relevant product information
6、in a clear and well-structured way to retain regular customers and also to attract new ones. In this context, the two key concepts that are related to online shopping are e-trust and interactivity (Merrilees and Fry, 2003). E-trust is building trusts related to web secure transaction, privacy of cus
7、tomer data, error free billing and credits on return items. Interactivity refers to the interaction between the site and a user of the site. The factors influencing the decision making of online consumers are web sites usability and interaction, online trust, and site contents elements including aes
8、thetic aspect of the online presentation and the marketing mix (Constantinides, 2004). Data mining is the process of discovering information like patterns, associations and future trends from large databases. Web usage mining is a data mining technique used to discover usage pattern, improve search
9、engine and personalize browsing in the web site. Profiling of users of a web site is therefore essential for retailer to better understanding their potential shoppers behaviour. In this context, pre-processing of web log files and traditional e-metrics computations show the significant difference be
10、tween weekday and weekend traffic, clicks, page views, visits and duration per click/page view/visit etc. including investigation of click paths through sequence analysis (Dellmann et al., 2003). Click stream data is an important tool in understanding online purchase behaviour. Statistical model bas
11、ed approach using dynamic multinomial probit model focuses on path analysis of the users choice path while visiting a web site and can be used to predict purchase conversion (Montgomery et. al., 2004). Researchers have also studied the relevant factors to analyze user choice of Internet portals. Hou
12、sehold-specific regression, a separate conditional logit regression of each household was used for the portal choice (Goldfarb and Qiang, 2006). To get insight into customer behaviour, new e-metrics designed by Net Genesis, present a handful of fundamentally information on stickiness, slipperiness,
13、focus, velocity and seducible moments ( Model based cluster analysis for web users sessions identify the patterns and similarities of user navigation and the relation between clusters can be interpreted using correspondence map of web pages (Pallis et al., 2007).Today, the web retailer can assess ho
14、w current and potential customers are responding to its web channel in real time. Therefore, retailer takes actions by deflecting a greater number of customer care interactions through chat channel rather than costly phone and email channel. The implementation of online chat service not always deliv
15、ers specific results like sales conversion and revenue. The retailer has to concentrate on the traffic volume, hot leads, sales conversion, service deployment resource and training cost etc. Therefore, a service solution which can identify and proactively target visitors on real time basis, rule bas
16、e methodology to prioritise important customers, and extensive domain expertise agents ensured incremental revenue with customer satisfaction and retention. In this paper, the authors focus on modelling and a methodology to optimize real time chat providing web funnel, ensure increased conversion rate and sales revenue by selecting the right hot leads and filtering
