Predicting Patent Life Using Robust Ensemble Algorithm

Increasing macroeconomic uncertainty necessitates that firms optimize their R&D investment and commercialization strategies. Patents, as crucial outcomes of R&D with legal protection, impose significant costs due to progressively increasing maintenance fees. Predicting patent life accurately thus becomes critical for effective patent management. Previous studies have often and primarily employed classification models for patent life prediction, while limiting practical utility due to coarse granularity. This study proposes a robust ensemble regression model combining multiple machine learning techniques, such as Random Forest and deep neural networks, to directly predict patent life. The proposed model achieved superior performance, surpassing individual baseline models, and recorded a Mean Absolute Error (MAE) of approximately 852.81. Additional validation with active patents further demonstrated the model’s practical feasibility, showing its potential to support sustainable intellectual property management by accurately predicting longer life for high-quality patents currently maintained. Consequently, the proposed model provides ongoing firms and brand-new startups with a decision support tool for strategic patent maintenance and commercialization decisions. By promoting efficient allocation of R&D resources and reducing unnecessary maintenance of low-value patents, the approach fosters sustainable management of innovation assets, enhancing predictive accuracy and long-term applicability.