Community Detection and Growth Potential Prediction Using the Stochastic Block Model and the Long Short-term Memory from Patent Citation Networks

TL;DR

This paper proposes a method combining stochastic block models and LSTM neural networks to cluster patent citation networks and predict their future growth potential, aiding technology management and investment decisions.

Contribution

It introduces the use of nested stochastic block models for patent network clustering and applies LSTM for predicting cluster growth, which is novel in this context.

Findings

Nested SBM is suitable for patent citation network clustering.

LSTM achieves over 50% direction accuracy in growth prediction.

High MAPE indicates effective citation growth modeling.

Abstract

Scoring patent documents is very useful for technology management. However, conventional methods are based on static models and, thus, do not reflect the growth potential of the technology cluster of the patent. Because even if the cluster of a patent has no hope of growing, we recognize the patent is important if PageRank or other ranking score is high. Therefore, there arises a necessity of developing citation network clustering and prediction of future citations. In our research, clustering of patent citation networks by Stochastic Block Model was done with the aim of enabling corporate managers and investors to evaluate the scale and life cycle of technology. As a result, we confirmed nested SBM is appropriate for graph clustering of patent citation networks. Also, a high MAPE value was obtained and the direction accuracy achieved a value greater than 50% when predicting growth potential for each cluster by using LSTM.