SPADE: an efficient algorithm for mining frequent sequences
Machine Learning
Multi-dimensional sequential pattern mining
Proceedings of the tenth international conference on Information and knowledge management
ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering
The PSP Approach for Mining Sequential Patterns
PKDD '98 Proceedings of the Second European Symposium on Principles of Data Mining and Knowledge Discovery
Sequential PAttern mining using a bitmap representation
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining Sequential Patterns by Pattern-Growth: The PrefixSpan Approach
IEEE Transactions on Knowledge and Data Engineering
Mining Sequential Patterns from Multidimensional Sequence Data
IEEE Transactions on Knowledge and Data Engineering
HYPE: mining hierarchical sequential patterns
DOLAP '06 Proceedings of the 9th ACM international workshop on Data warehousing and OLAP
M2SP: mining sequential patterns among several dimensions
PKDD'05 Proceedings of the 9th European conference on Principles and Practice of Knowledge Discovery in Databases
Assisting scientific discovery with an adaptive problem solver
DS'05 Proceedings of the 8th international conference on Discovery Science
| Hi-index | 0.01 |
Data warehouses contain large volumes of time-variant data stored to help analysis. Despite the evolution of OLAP analysis tools and methods, it is still impossible for decision makers to find data mining tools taking the specificity of the data (e.g. multidimensionality, hierarchies, time-variant) into account. In this paper, we propose an original method to automatically extract sequential patterns with respect to hierarchies. This method extracts patterns that describe the inner trends by displaying patterns that either go from precise knowledge to general knowledge or go from general knowledge to precise knowledge. For instance, one rule exhibited could be data contain first many sales of coke in Paris and lemonade in London for the same date, followed by a large number of sales of soft drinks in Europe, which is said to be divergent(as precise results like coke precede general ones like soft drinks). On the opposite, rules like data contain first many sales of soft drinks in Europe and chips in London for the same date, followed by a large number of sales of coke in Parisare said to be convergent. In this paper, we define the concepts related to this original method as well as the associated algorithms. The experiments which we carried out show the interest of our proposal.