Software

The new Version 1.2.5 of the prudsys XELOPES Data Mining library has been released.

The XELOPES library is an open platform-independent and data-source-independent library for Embedded Data Mining. It was developed in close cooperation between the German Data Mining specialist prudsys AG and the Russian MDA specialist ZSoft Ltd.

Version 1.2.5 contains a new package of Reinforcement Learning (RL) algorithms from the fields of Dynamic Programming, Monte Carlo methods, and Temporal-Difference Learning. New sequence analysis algorithms have been included. Additionally, these algorithms are combined with RL to optimize recommendations. New data access classes, especially for log files, have been added, too.

Further, the first Russian Data Mining textbook "Methods and Models of Data Analysis: OLAP and Data Mining" (in Russian) from A. Barseghyan, M. Kupryanov, V. Stepanenko, and I. Kholod has been released. It describes the XELOPES library for the solution of Data Mining problems and contains a CD with a XELOPES release.

The XELOPES library that can be downloaded and is licensed under the GNU General Public License.