本研究以專利分析探討美國製藥業產業的公司績效,並以倒傳遞類神經網絡以及自我組織映射網路的方式進行分析,探討發明人數、專利範疇及專利活動年期對公司績效的影響,專利分析的資訊來源為美國專利商標局(USPTO),而財務資料則來自COMPUSTATE。研究結果發現,發明人數對公司績效的影響呈現正向的影響,此外專利範疇對公司績效也是正向影響,最後專利活動年期對公司績效同樣具有正向的影響。因此本研究建議美國製藥公司應積極匯聚優秀發 明人才以培養競爭優勢,定期評估其所耗費的資源是否得到最適的配置,並且持續將資源投入在研發新藥並取得專利,以求讓公司績效更加提升。
This study uses patent analysis to explore the corporate performance of the American Pharmaceutical industry by use of back-propagation network (BPN) of artificial neural network (ANN) and Self-Organizing Map (SOM). Besides, this paper explores the influence of number of inventors, patent scope, and activity year of patent upon the corporate performance. The patent data are collected from United States Patent and Trademark Office (USPTO), and financial data are collected from the database of COMPUSTAT. We find that number of inventors has a positive effect on corporate performance, while patent scope and activity year of patent also have positive effect on it. Based on our findings, we suggest that the American pharmaceutical companies should put their resources persistently in the development of new drugs and obtain their patents. Also they can accumulate the outstanding inventors to develop company's competitive advantage.