Entrepreneurs may use a Decision Model which is a computer based system that predicts the outcomes of decisions. The relationships between elements of the decision and the forecasted results are mapped in order to understand or control problems. The decision model may also predict what will happen if a certain action is taken.

The matrix of INESS agent will be based on the techniques of data mining science. Data mining helps modern companies to focus on the most important elements of their data warehouses. By using this powerful tool, it is possible to predict future behaviours and successful business decisions.

A definition close to this purpose was given by Ellen Monk and Bret Wagner (2006) "Data mining: the statistical and logical analysis of large sets of transaction data, looking for patterns that can aid decision making.” [5]

Data Mining is an iterative process consisting of a series of steps which lead to the collection of data on the discovery and extraction of useful information from them:

• Data Cleaning: In this step, are removed from the database those producing noise, i.e., all those elements which may affect or distort the result.
• Data Integration: In this step, the inhomogeneous data that was collected from multiple sources are integrated into one database.
• Data Selection (Data selection): Of all the available data, carefully selected those that are relevant and useful for the analysis to follow.
• Data Transformation: The selected data are modified so that their form is suitable for the extraction process.
• Data Mining: Is the most important steps of the process and that's why at this stage, a variety of sophisticated techniques (decision trees, neural networks, genetic algorithms, rule induction, etc.) are used to extract potentially useful standards.
• Pattern evaluation: This step recognized useful patterns representing knowledge, specific evaluation measures (evaluation measures).
• Knowledge Representation: In this final step, the knowledge that has been discovered is presented to the user, thus helping to understand and interpret the results of data mining.

At this point, it should be mentioned that the user, has the ability to modify the assessment measures to perfect the extraction process to select new data to further amend existing or incorporate based news from new sources, with the ultimate aim of drawing different and more relevant results.

The aim of the present research is to propose the development of a virtual agent for entrepreneurs by simulating the entrepreneurial activity and personality. This ambitious software will take advantage of the vast amounts of information existing inside the business environment, but also the big data that are flooding the network. The agent will be able to suggest the optimum decision to the entrepreneur based on a holistic evaluation of variables and factors. The development of this powerful tool can definitely strengthen individual entrepreneurship as far the entrepreneur usually has no access to big-scale data and it is not possible to assess all available information.

1. N. R. Jennings , T. J. Norman , P. Faratin , P. O'Brien & B. Odgers (2000) Autonomous agents for business process management, Applied Artificial Intelligence, 14:2,145-189, DOI: 10.1080/088395100117106
2. Kuziot & Vasileiadis (2012) Mapping Entrepreneurship Competencies as a Horizontal Professional Function onto NQF and EQF levels, NAUKA I GOSPODARKA NR 1 (12) 2012.
3. Dietrich, C. (2010). "Decision Making: Factors that Influence Decision Making, Heuristics Used, and Decision Outcomes." Inquiries Journal/Student Pulse, 2(02). http://www.inquiriesjournal.com/a?id=180
4. Wooldridge, M., & Jennings, N. (1995). Intelligent agents: Theory and practice. The Knowledge Engineering Review, 10(2), 115-152
5. Ellen Monk, Bret Wagner Concepts in Enterprise Resource Planning, Thomson Course Technology, Boston 2006
6. Gregory Piatetsky-Shapiro, William J. Frawley: Knowledge Discovery in Databases. AAAI/MIT Press 1991, ISBN 0-262-62080-4
7. D. Hand, H. Mannila, P. Smyth Principles of Data Mining. MIT Press, Cambridge 2001