Algebra for Complex Analysis of Data
| Authors | |
|---|---|
| Year of publication | 2020 |
| Type | Article in Proceedings |
| Conference | International Conference on Database and Expert Systems Applications |
| MU Faculty or unit | |
| Citation | |
| Web | https://link.springer.com/chapter/10.1007/978-3-030-59003-1_12#citeas |
| Doi | http://dx.doi.org/10.1007/978-3-030-59003-1_12 |
| Keywords | data analysis; analytical algebra; similarity; pattern mining |
| Description | In data science, the process of development focuses on the improvement of methods for individual data analytical tasks. However, their combination is not properly researched. We believe that this situation is caused by a missing framework, that would focus solely on data analytical tasks, instead of complicated transformation between individual methods. In this paper, a new analytical algebra is defined. This algebra is based on a flat structure of transaction file and operations over it. As a part of the paper, definitions of several data analytical tasks are proposed. Algebra is recursive and extendable. As an example of usability of the algebra, one complex analytical task created by a combination of analytical operators is described. |
| Related projects: |