Location
Hilton Waikoloa Village, Hawaii
Event Website
https://hicss.hawaii.edu/
Start Date
7-1-2025 12:00 AM
End Date
10-1-2025 12:00 AM
Description
Numerous scholars have delved into the primary factors influencing patent licensing, yet the relationships between licensors, licensees, and licensed patents require further exploration. This study proposes using Graph Convolutional Networks (GCN) to analyze these relationships and predict future patent licensing. Utilizing data from the United States Patent and Trademark Office (USPTO) assignment dataset, we extract features such as company technological capabilities, domains, licensed patents, International Patent Classifications (IPCs), and network similarity. Our proposed GCN model aims to enhance strategic planning for companies and provide insights into future technological trends. Experimental results demonstrate that the GCN model outperforms traditional machine learning methods, offering improved accuracy in predicting patent licensing and valuable guidance for corporate strategy development.
Recommended Citation
Lai, Chia-Yu; Dai, Jhih-Huan; and Hsu, Yueh-Teng, "Predicting Patent Licensing Using Graph Convolutional Networks (GCN)" (2025). Hawaii International Conference on System Sciences 2025 (HICSS-58). 3.
https://aisel.aisnet.org/hicss-58/ks/knowledge_flows/3
Predicting Patent Licensing Using Graph Convolutional Networks (GCN)
Hilton Waikoloa Village, Hawaii
Numerous scholars have delved into the primary factors influencing patent licensing, yet the relationships between licensors, licensees, and licensed patents require further exploration. This study proposes using Graph Convolutional Networks (GCN) to analyze these relationships and predict future patent licensing. Utilizing data from the United States Patent and Trademark Office (USPTO) assignment dataset, we extract features such as company technological capabilities, domains, licensed patents, International Patent Classifications (IPCs), and network similarity. Our proposed GCN model aims to enhance strategic planning for companies and provide insights into future technological trends. Experimental results demonstrate that the GCN model outperforms traditional machine learning methods, offering improved accuracy in predicting patent licensing and valuable guidance for corporate strategy development.
https://aisel.aisnet.org/hicss-58/ks/knowledge_flows/3