Implicit Multi-Feature Learning for Dynamic Time Series Prediction of the Impact of Institutions

摘要: Predicting the impact of research institutions is an important tool for decision makers, such as resource allocation funding bodies. Despite significant effort adopting quantitative indicators to measure institutions, little known that how evolves in time. Previous studies have focused on using historical relevance scores different predict potential future these institutions. In this paper, we explore factors can drive changes finding institution, measured by number accepted papers more determined authors’ influence institution. Geographic location institution feature and state GDP Identifying features allows us formulate a predictive model integrates effects individual ability, GDP. The unveils underlying driving which be used accurately