Name
Abstract | ||
|---|---|---|
Mining sequential patterns only considers the sequential purchasing behaviors for most of the consumers. We can use this information to predict what products the consumers would like to purchase next time, but we cannot use this information to predict when the consumer will need the products in the future, that is we cannot know when the products need to be promoted to the consumers. In order to effectively predict the next purchased time for the products, only the consumable products will be considered, since the next purchased time for a consumable is always related to the purchased quantity of this product purchased at this time. Although single gains for consumable products may be lower than that of appliances or electronic products, the accumulative gains for consumable products are considerable. Therefore, grasping suitable timing to do sales promotion for consumable products is an important task. In this paper, we propose a novel data mining approach to find the consumption behaviors for most of the consumers. From this information, we can predict the next purchased time for a product according to the purchased quantity of this product purchased at this time. However, there may be various consumption behaviors for the consumers. We also consider the associations between the consumption behaviors and the properties of the consumers, and therefore we can predict the next purchased time of a product for a consumer according to the properties of the consumer and the purchased quantity of the product purchased at this time. The experimental results show that our algorithm is efficient and scalable, and the mining results can exactly reflect the consumption behaviors for most of the consumers. |
Year | Venue | Keywords |
|---|---|---|
2016 | JOURNAL OF INFORMATION SCIENCE AND ENGINEERING | data mining,consumption pattern,consumption association rule,sequential pattern,transaction database |
Field | DocType | Volume |
Data mining,Computer science,Association rule learning,Distributed computing | Journal | 32 |
Issue | ISSN | Citations |
2 | 1016-2364 | 0 |
PageRank | References | Authors |
0.34 | 5 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Show-Jane Yen | 1 | 537 | 130.05 |
| Chiu-Kuang Wang | 2 | 29 | 3.10 |
| Yue-Shi Lee | 3 | 543 | 41.14 |