Classifying purchase decision based on user clickstream in E-Commerce using web usage mining

Surya Yehezki, Arian Dhini

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

The advance of internet usage in Indonesia gives positive impact on the development of e-commerce in Indonesia where 63.5% of internet users have made online transactions. Along with ecommerce B2C growth in Indonesia, firm needs for an effective promotional strategy to understand the preferences and potential purchases for each consumer to increase return on investment (ROI). This empirical study investigated purchase decision of ecommerce users using Web Usage Mining framework. The high combination of purchasing product categories by users of ecommerce website required a multi-label classification technique that could classify those pair of purchase decision. Label Powerset method with Support Vector Machine (SVM) algorithm was applied to classify e-commerce users purchase decisions using general and detailed information features. Feature selection using Information retained 60 from 90 features. The proposed feature selection with Information Gain and parameter selection using Grid Search proved that they had an ability to enhance performance to classify purchase decision of e-commerce user. Radial Basis Function (RBF) as the most effective kernel presented an accuracy of 75.6%, with slightly difference of 2.2% with classification without using feature selection.

Original languageEnglish
Title of host publication2017 International Conference on Business and Information Management, ICBIM 2017
PublisherAssociation for Computing Machinery
Pages57-61
Number of pages5
ISBN (Electronic)9781450352765
DOIs
Publication statusPublished - 23 Jul 2017
Event2017 International Conference on Business and Information Management, ICBIM 2017 - Beijing, China
Duration: 23 Jul 201725 Jul 2017

Publication series

NameACM International Conference Proceeding Series
VolumePart F131932

Conference

Conference2017 International Conference on Business and Information Management, ICBIM 2017
CountryChina
CityBeijing
Period23/07/1725/07/17

Keywords

  • Label Powerset
  • Multi Label Classification
  • Support Vector Machine
  • Targeted advertising
  • Web usage mining

Fingerprint Dive into the research topics of 'Classifying purchase decision based on user clickstream in E-Commerce using web usage mining'. Together they form a unique fingerprint.

Cite this