Volume 10, Issue 1 (8-2023)
J Entrepreneurial Strategies Agric 2023, 10(1): 107-117 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Siah Siahsarani Kojuri M A. (2023). Presenting and Explaining the Predictive Model of Students' Entrepreneurial Future with an Emphasis on Business Intelligence Indicators. J Entrepreneurial Strategies Agric. 10(1), 107-117. doi:10.61186/jea.10.19.107
URL: http://jea.sanru.ac.ir/article-1-349-en.html
URL: http://jea.sanru.ac.ir/article-1-349-en.html
Department of Management, Entrepreneurship Research Group, Strategic Studies of Cooperation, Development and Social Welfare Institute, Golestan University, Gorgan, Iran
Abstract: (3215 Views)
Extended Abstract
Background: The issue of employment and guiding the population of university graduates towards entrepreneurship has long been one of the most challenging and favored topics among researchers in this field. One fundamental question in this area is why, in relatively similar situations and contexts, some university graduates identify and pursue entrepreneurial opportunities, while others do not possess this ability. The answer to this multifaceted question can be explored from various dimensions, one of which—business intelligence indicators—has been considered crucial in shaping the entrepreneurial future.
Methods: In the first step, a literature review and analysis of research in the field of entrepreneurship and its relationship with business intelligence were conducted to identify 13 dimensions of business intelligence that can effectively influence the entrepreneurial future. In the second step, quantitative methods in data mining (both descriptive and predictive) were utilized to analyze the statistical population. To describe the research community, 401 students from Gorgan University of Agriculture and Natural Resources in 1401 were grouped and analyzed into three separate clusters using the Davis-Bouldin index. Additionally, artificial neural networks were employed to design a predictive model for assessing the entrepreneurial future of the students.
Results: The research findings revealed a significant difference among students in the statistical population regarding their business intelligence capabilities. Based on the identified business intelligence indicators, students can be categorized into three distinct clusters. The results from the modeling stage of predicting students' entrepreneurial futures using neural networks demonstrated that business intelligence indicators possess a high predictive ability, allowing for changes in the dependent variable to be predicted with an accuracy of 0.925. Furthermore, the results of the sensitivity analysis confirmed the importance of demographic variables and their impact on shaping the entrepreneurial future.
Conclusion: According to the results of the current research, it can be concluded that students differ significantly in their business intelligence indicators, which can play a vital role in determining their entrepreneurial futures. Therefore, it is recommended that business intelligence indicators be strengthened and enhanced through skill training courses, consideration of these indicators during the student selection process, provision of practical courses at the university, strengthening the relationship between industry and academia, and introducing successful entrepreneurs to students.
Methods: In the first step, a literature review and analysis of research in the field of entrepreneurship and its relationship with business intelligence were conducted to identify 13 dimensions of business intelligence that can effectively influence the entrepreneurial future. In the second step, quantitative methods in data mining (both descriptive and predictive) were utilized to analyze the statistical population. To describe the research community, 401 students from Gorgan University of Agriculture and Natural Resources in 1401 were grouped and analyzed into three separate clusters using the Davis-Bouldin index. Additionally, artificial neural networks were employed to design a predictive model for assessing the entrepreneurial future of the students.
Results: The research findings revealed a significant difference among students in the statistical population regarding their business intelligence capabilities. Based on the identified business intelligence indicators, students can be categorized into three distinct clusters. The results from the modeling stage of predicting students' entrepreneurial futures using neural networks demonstrated that business intelligence indicators possess a high predictive ability, allowing for changes in the dependent variable to be predicted with an accuracy of 0.925. Furthermore, the results of the sensitivity analysis confirmed the importance of demographic variables and their impact on shaping the entrepreneurial future.
Conclusion: According to the results of the current research, it can be concluded that students differ significantly in their business intelligence indicators, which can play a vital role in determining their entrepreneurial futures. Therefore, it is recommended that business intelligence indicators be strengthened and enhanced through skill training courses, consideration of these indicators during the student selection process, provision of practical courses at the university, strengthening the relationship between industry and academia, and introducing successful entrepreneurs to students.
Keywords: Artificial neural network, Business, Clustering, Entrepreneurship, Market intelligence
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
