Identifying Emerging Trends of Financial Business Method Patents

Abstract

Financial technology has become an important part of the banking industry in recent times. This study attempts to propose a framework to identify emerging areas and trends using financial business method patents. Based on the abstracts of financial business method patents registered at the United States Patent and Trademark Office, this study first applies latent Dirichlet allocation to identify emerging topics. The probability of the annual occurrence of each topic is adjusted through the exponentially weighted moving average to reflect the importance of the recent probability of topics. Each topic is classified as "hot" or "cold" depending on whether the exponentially weighted moving average of the probabilities exceeds the threshold. We applied survival analysis to the time gap of recurrently becoming hot from a cold status with the associated factor of financial business method patents. The findings suggest that the topic with the short granted period and high forward citation is likely to become hot. In addition, the topic that is aged and specific in narrow areas is likely to continuously change into the hot or cold status. The approach proposed in this study contributes toward understanding topic emergence in the financial area and pursuing sustainable development.

Exploring Knowledge Trajectories of Accounting Information Systems Using Business Method Patents and Knowledge Persistence-Based Main Path Analysis

“…This characteristic generates fluent knowledge flows, and so the statistical power and validity of patent citation frequency-based metrics are often increased. Therefore, business method patents have been widely used for many quantitative studies [15][16][17][18].…”

Classification of FinTech Patents by Machine Learning and Deep Learning Reveals Trends of FinTech Development in China

“…However, these methods can only measure the FinTech innovation carried out by the financial sectors and cannot cover other sectors. Lee and Sohn [28] found that FinTech-related technological innovation could be found in patents, and the theme of FinTech innovation could be mined based on text analysis. However, due to the lack of annotated patents and corresponding datasets, there are few studies on FinTech patent identification based on machine learning or deep learning models.…”

TopicTracker: A Platform for Topic Trajectory Identification and Visualisation

“…Topic trajectory identification is a research area that has attracted significant attention from scientific institutions and innovation-industry sectors. In this area, a fundamental is the use of topic modeling to discover latent thematic topics (or concepts) from a document collection, where each topic consists of its representative terms extracted from the collection [1]. More recently, dynamic topic modeling has also been utilised to identify topics and their evolution over a time period [2,3,4].…”

“…An example of M is given in Table 4. To estimate TESs in M, the concept of similarity has been widely used in most related works [9,5,11,16,1,3]. The fundamental is to formulate a similarity measure between x and y using the aggregated similarities between x's top-k descriptive terms and y's top-k descriptive terms (often K=10) [19,3].…”