Scholarly record
INTEGRATION OF STRUCTURED AND UNSTRUCTURED DATA IN THE ANALYSIS OF E-COMMERCE CUSTOMERS
Abstract
The main reason for the rapid development of e-commerce is the possibility of personalization and individual customer service. Modern e-commerce systems have diverse and well-developed capabilities to analyse and manage customer relationships. In most cases, however, these analytical systems are based on processing and analysis of structured customer data, those that are collected at registration and stored in the database. It is important to note that many of the customers when completing registration forms do not always fill in their data properly because of the lack of sufficient motivation or for security reasons. In addition, it is sometimes difficult to derive sufficiently detailed information about customer behavior from this data alone. What's more - in this case one of the major challenges to the development of e-commerce is the search for and use of additional data sources for customers. That is why we propose for business analyses in the field of electronic commerce the integrated use of the data accumulated in the databases and the data obtained from the processing of unstructured information, deriving mainly from additional surveys and from different Internet sources. Data Mining Methods were used to analyze the resulting integrated data, and the approbation was done with a RapidMiner software product.
Publication Impact Profile
Publication details
References4
J. R. Quinlan (1986). Induction of Decision Trees. DOI: 10.1023/a:1022643204877
Snezhana Sulova (2017). USING TEXT MINING TO CLASSIFY RESEARCH PAPERS. DOI: 10.5593/sgem2017/21/s07.083
Ian H. Witten (2008). Data Mining. http://dl.acm.org/citation.cfm?id=1207405
John Van Ryzin; Leo Breiman; Jerome H. Friedman; Richard A. Olshen; Charles J. Stone (1986). Classification and Regression Trees.. DOI: 10.2307/2288003
Citing literature
Number of times cited according to Crossref: 2
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.

