A Decision Support Tool using Machine Learning Techniques for Classification of Business Startups’ Ability to Secure Funding
Open AccessHalf of new business startups in the United States fail within five years, resulting in a significant economic loss since these startups generate millions of new jobs annually. The low survival rate is partially owing to the failure of these startups to secure adequate external funding. Considering the often-immature cash flow of startups and the inability to self-fund, access to external finances is essential. However, from the investors’ perspective, startup investment is associated with high levels of financial risk and is usually based on early signals of the startup’s intellectual capital.The predictability of access to funding and the understanding of the signals of intellectual capital that correlate with the ability to secure funding are of paramount importance. Entrepreneurs may use that knowledge to increase their probability of success. Investors can use that knowledge to inform better investment decisions.The existing literature fails to address methods of predicting a startup business’s ability to attract external funding. Instead, current work is limited to understanding the existence and direction of correlation between the various signals of a business startup’s intellectual capital and the ability to raise external funding. The findings of the existing research varied and were at times contradictory. This praxis is the first, and only known, work that builds a Machine Learning (ML) based decision support tool, assisting entrepreneurs and investors’ decision making by forecasting business startup’s ability to secure funding. The relatively large and recent database used in this work, enable further arbitration of literature’s inconsistent findings.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.