TITLE

Learning Approach for Selecting Key Organization Components Influencing Enterprises Performance

AUTHOR(S)
Pudil, Pavel; Tripes, Stanislav; Somol, Petr; Pirozek, Petr
PUB. DATE
February 2014
SOURCE
Proceedings of the International Conference on Management, Leade;2014, p222
SOURCE TYPE
Conference Proceeding
DOC. TYPE
Article
ABSTRACT
The issue of the success of enterprises is often discussed within the academic community. There are many approaches to measuring the performance of enterprises. The main purpose of our research is to find the most important factors influencing organizational performance. The success of enterprises does not depend only on their financial results but on all the components of the organization. In our paper, the performance assessment is based on Return of Assets (ROA). Our dataset consists of 178 enterprises in the Czech business environment from the values in 2011 and 2012. The dataset was collected in enterprises from different industries, type of ownership, legal form and size of the organization. The enterprises were divided into two groups: "Under average ROA" and "Above average ROA". A closer view on variables provides information about the dynamics of the environment; the dimension of organizational structure; the approach to determining competences and forming the organizational structure. Data about the strategy shows the organizations choice of type of strategy (low-cost, hybrid or differentiation approach), the degree of definition of the organization's competitive advantage and the formulation of strategy on different levels (functional, business and corporate). The corporate culture gives evidence about the tools, approaches and behaviour, which leads to achieving corporate goals. An important role is also played by the power and type of the culture (power, task, role and person). Among the factors influencing corporate performance, organizational governance based on the Two-dimensional Governance Matrix undoubtedly plays a role here (introduced in our previous work). Our goal is to find a subset of the most important variables that provide the best possible discrimination between successful and unsuccessful enterprises. We used the Sequential Forward Floating Search (SFFS) algorithm from statistical pattern recognition as the means of achieving this goal. This method is generally used for selecting the most informative features in classification and learning. In the case of our paper, we have used as a tool for finding the key performance factors. The novelty of our approach is based on interdisciplinary cooperation between the management of organizations and on the other hand learning approaches of statistical pattern recognition.
ACCESSION #
94947565

 

Share

Read the Article

Courtesy of THE LIBRARY OF VIRGINIA

Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics