Building An Online Purchasing Behavior Analytical System With Neural Network

Abstract

With the rapid growth of the worldwide online sales, it is very important to analyze the factors influencing online purchasing behaviors. The analysis of the data on online customers has not been given adequate effort. The difficulty of accurate assessment of online customer behaviors is due to its complexity, disorganized knowledge about it, and the lack of effective and valid tools to measure and predict it. The technology of data mining has provided the opportunity to extract interesting knowledge from large amount of data. Since the back-propagation neural network (BPNN) is one of the most powerful general nonlinear modeling techniques, we have built a back office analytical system based on it and returned our classification and prediction results back to the consumer. The purpose of the research is to develop a system to help better understand customer online purchasing behaviors and to assist the customer relationship management campaigns of e-business enterprises. The system aims to classify online customers and predict their purchasing behaviors according to their demographics and attitudes toward online shopping. The data used for model building and testing was collected through a website. A group of students at City University of Hong Kong participated in the data collection process to provide their online shopping behaviors. To evaluate the performance of the proposed system, we compare it with other mature classification tools, namely, K-means clustering and multiple discriminate analysis (MDA) tools. The results show better precision with the designed

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.