학술논문

Green Pioneers in the Maze of Sustainability: Machine Learning Insights into the Drivers of Eco-Entrepreneurship
Document Type
Conference
Source
2024 International Conference on Distributed Computing and Optimization Techniques (ICDCOT) Distributed Computing and Optimization Techniques (ICDCOT), 2024 International Conference on. :1-8 Mar, 2024
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
General Topics for Engineers
Photonics and Electrooptics
Robotics and Control Systems
Support vector machines
Logistic regression
Machine learning algorithms
Planets
Green products
Entrepreneurship
Predictive models
NIT
Green Entrepreneurship Behaviors
Sustainable development
Machine learning
Language
Abstract
Background : This study seeks to identify the elements that motivate students to pursue green entrepreneurship. In order to help achieve sustainable development objectives, it aims to comprehend how students from NIT's views on environmental sustainability and their confidence in their own entrepreneurial talents impact the choice to launch environmentally conscious companies. Methods Used: Collecting data via a structured questionnaire centered on green qualities, opportunity recognition, green attractiveness, and entrepreneurial skills, the research used a mix of qualitative and quantitative methodologies. Key determinants of green entrepreneurship activity were identified by analyzing the replies using several machine learning algorithms. While previous research has shown that environmentally conscious business practices are important, no one has yet developed a model that takes into account individual characteristics, environmental factors, and legal requirements to foretell how an entrepreneur would behave under a green light. This study addresses a gap in the existing literature by presenting a new paradigm that explains the roles of regulatory frameworks and environmental knowledge as mediating and moderating factors, respectively, in influencing green entrepreneurship behavior. Results Achieved: Early findings from machine learning analysis indicate a robust relationship between the tendency to participate in green entrepreneurship and an individual's green desirability, opportunity perception, and entrepreneurial skill. The importance of these parameters in forecasting green entrepreneurial intents was shown by the strong predictive performance of models like Logistic Regression and AdaBoost classifiers exhibit superior performance. Concluding Remarks: This study presents a novel research framework that looks at how green attributes and entrepreneurial skills affect green entrepreneurship behavior. It then takes a look at how regulatory frameworks and environmental knowledge mediate this relationship, and how it all adds up to sustainable development.