SmartFund: Predicting Research Outcomes with Machine Learning and Natural Language Processing

The mission of the National Science Foundation (NSF) is to promote progress of science. It supports fundamental research and education in science and engineering. It provides funding for researchers to explore a variety of disciplines in thousands of institutions across the United States. The outcomes of such research projects vary widely and with much funding being funneled into these projects, it would be efficient and cost-effective to be able to predict these outcomes so the NSF can make informed decisions on the amount of funding they allocate to future projects. We consider a variety of factors that point to general trends and use a combination of natural language processing techniques (such as topic models and phrase mining) and neural networks to predict how many papers and citations will come from potential research projects seeking funding.