Modern Instruments for Data Analysis
On October 14 the Data Mining in R Workshop was held at St.Petersburg School of Economics and Management. Professor of the Cracow University of Economics Paweł Lula (Department of Computational Systems) introduced participants to the data analysis with the R Project for Statistical Computing software.
R is a free software environment for statistical computing and graphics. HSE academic supervisor of the Management and Analytics programme professor Angel Barajas underlined the big potential of using R for research. R provides a wide variety of statistical (linear and nonlinear modelling, classical statistical tests, time-series analysis, classification, clustering, etc.) and graphical techniques, and is highly extensible. He also expressed interest in Multilayer Perceptron Model and Neural Network Model.
Department of Computational Systems, Cracow University of Economics
Extremely high rate of development of all spheres of our life causes that we must analyze and process a huge amount of heterogeneous and complex information. Very often this task is impeded by the lack of an adequate theory describing observed phenomena. These factors constitute main determinants of data mining approach in data analysis. According to Usama Fayyad (one of the most famous American data scientist) defined data mining as a nontrivial process of identifying valid, novel, potentially useful, and ultimately understandable patterns in data. Data mining approach merges ideas, methods and techniques from mathematics, statistics, computer science, optimization, linguistics, graphics, biology and other fields. These sophisticated methods are not only very interesting from theoretical point of view, but also very useful in practice.
My research and didactic activity is very strongly connected with data mining techniques, especially with exploratory text analysis. We work on these topics on Cracow University of Economics together with my colleagues and my students. I am very glad that I have run a seminar on this topic here, in St. Petersburg. It was a great pleasure for me to meet students with excellent mathematical and statistical background and very good programming skills. Also I had a possibility to talk with my colleagues working at the HSE about their experience with data analysis. I am convinced that our cooperation on data mining problems will allow us to find the best patterns of cooperation between our institutions, professors and students.