A Combination Model to Predict the type of Customer Needs in Online Book Sales: A Case Study of Adinehbook Online Bookstore
Purpose: To predict the type of customer needs of online bookstores by using data mining methods based on Kano model. Methodology: First, three groups of needs and factors affecting customer satisfaction of Adinehbook online store were extracted according to expert opinions and then the Kano questio...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Iran Public Libraries Foundation
2018-12-01
|
| Series: | تحقیقات اطلاعرسانی و کتابخانههای عمومی |
| Subjects: | |
| Online Access: | http://publij.ir/article-1-1800-en.pdf |
| Summary: | Purpose: To predict the type of customer needs of online bookstores by using data mining methods based on Kano model.
Methodology: First, three groups of needs and factors affecting customer satisfaction of Adinehbook online store were extracted according to expert opinions and then the Kano questionnaire was designed based on these factors. After data preprocessing, the type of each customer's needs were determined based on the Kano model. So customers were clustered according to the type of needs and demographic characteristics. Clustering was done using K-means algorithm and the number of initial clusters were determined by self-organizing neural network. Then the frequency of customer needs in each cluster were prioritized and the clusters were classified accordingly. In the next step, a decision tree technique was used to predict future customer needs.
Findings: Results of the decision tree showed that among the demographic variables, education, age, gender and marital status had the greatest impact on determining the type of customer needs.
Originality/value: Using the result of research, online bookstores such as Adinehbook can first identify the customer class which determines the type of their needs by considering their demographics and then apply the appropriate strategy and performance to treat the customer. |
|---|---|
| ISSN: | 2645-5730 2645-6117 |