Deep learning and natural language processing for innovation detection in FinTech
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Advancements in technology have resulted in the emergence of numerous FinTech innovations. However, a global understanding of such innovations is limited, due to a lack of an underlying taxonomy and benchmark datasets in the FinTech domain. To address this limitation, we develop a FinTech taxonomy and manually annotate a set of FinTech patent abstracts according to the taxonomy. We use the annotated dataset to train deep learning models. Experimental results show that the deep learning models can accurately identify FinTech innovations. Specifically, we focus on patent document classification, and explores the predictive capabilities of three document sections alone and in combination. Our results indicate that the title and abstract in combination are most efficient in detecting FinTech innovations.