Patterns of technology life cycles: stochastic analysis based on patent citations

Patent analysis has been considered as an effective means of estimating phases of a technology life cycle. However, previous studies have not considered the dynamic and idiosyncratic aspects of a technology's progression since they were based on deterministic methods, mainly fitting s- or double s-shaped curves to patent application counts. Moreover, previous methods cannot be executed at the individual patent level. We propose a stochastic technology life cycle analysis to trace the phases of a technology's progression based on patent citations and identify the patterns of technology life cycles at the individual patent level. At the heart of the proposed approach are a hidden Markov model to estimate the probability of a system being at a certain hidden state from observation and cluster analysis to group a set of objects according to their similarities. A case study of patents about laser technology in lithography is presented.