Prediction of SMEs’ R&D performances by machine learning for project selection

Abstract

To improve the efficiency of government-funded research and development (R&D) programs for small and medium enterprises, it is necessary to make the process of selecting beneficiary firm objective. We aimed to develop machine learning models to predict the performances of individual R&D projects in advance, and to present an objective method that can be utilized in the project selection. We trained our models on data from 1771 R&D projects conducted in South Korea between 2011 and 2015. The models predict the likelihood of R&D success, commercialization, and patent applications within 5 years of project completion. Key factors for predicting the performances include the research period and area, the ratio of subsidy to research budget, the firm’s region and venture certification, and the average debt ratio of the industry. Our models’ precisions were superior to qualitative expert evaluation, and the machine learning rules could be explained theoretically. We presented a methodology for objectively scoring new R&D projects based on their propensity scores of achieving the performances and balancing them with expert evaluation scores. Our methodology is expected to contribute to improving the efficiency of R&D investment by supplementing qualitative expert evaluation and selecting projects with a high probability of success.

The Effect of the Commercialization Failure of SMEs’ R&D on Survival

“…The dependent variable is a binary variable set to one if the firm underwent early business closure, as extracted from a Korean credit rating agency (NICE Information Service). The success and performance of R&D projects are linked to the research area and the firm's R&D capabilities [12,57], potentially creating a source of endogeneity in commercialization failure outcomes that may impact our results. Therefore, our estimations required a two-step process in which the first step was a probit estimating the commercialization failure; and the second was an analysis for the early business closure.…”

“…Therefore, funding agencies should refrain from R&D support policies that blanket-target all types of firms and should make greater efforts to select beneficiaries whose proposals that are well-planned and highly likely to succeed. For example, as an auxiliary tool, it would be helpful to establish and apply a system using advanced machine learning techniques to predict which firms will have a high probability of success, instead of relying only on the qualitative judgment of expert committees [57]. This can be a means of increasing the efficiency of government R&D investment, and also a means to prevent firms that are not yet ready for innovation from prematurely undertaking costly and risky attempts that may lead to early business closure.…”