Drivers of the decrease of patent similarities from 1976 to 2021

TL;DR

This study investigates the declining trend in patent similarity over decades using advanced NLP tools and generalized additive models, revealing complex, temporally varying drivers behind this phenomenon.

Contribution

It introduces a computationally efficient NLP-based similarity measure and applies non-linear modeling to uncover diverse factors influencing patent similarity decline.

Findings

Non-linear models explain more variation in similarity scores.

An underlying trend in similarity scores differs from previous understandings.

The similarity decline is driven by multiple, temporally varying factors.

Abstract

The citation network of patents citing prior art arises from the legal obligation of patent applicants to properly disclose their invention. One way to study the relationship between current patents and their antecedents is by analyzing the similarity between the textual elements of patents. Many patent similarity indicators have shown a constant decrease since the mid-70s. Although several explanations have been proposed, more comprehensive analyses of this phenomenon have been rare. In this paper, we use a computationally efficient measure of patent similarity scores that leverages state-of-the-art Natural Language Processing tools, to investigate potential drivers of this apparent similarity decrease. This is achieved by modeling patent similarity scores by means of generalized additive models. We found that non-linear modeling specifications are able to distinguish between distinct, temporally varying drivers of the patent similarity levels that explain more variation in the data ($R^2\sim 18\%$) compared to previous methods. Moreover, the model reveals an underlying trend in similarity scores that is fundamentally different from the one presented previously.