Early warning of trends in commercial wildlife trade through novel machine-learning analysis of patent filing - Article summary and key findings

Aug 5, 2026

Upload by Ivy

Unsustainable wildlife trade threatens thousands of species, yet policy decisions often lag behind fast-changing commercial markets. This study introduces a novel machine-learning method to detect shifts by analyzing patent-filing trends from 1970–2020 for six traded taxa. Results identify 27,308 patents with 130% per-year increases, show innovation-driven diversification and examples such as illegal-to-trade rhinoceros horn products and new pangolin farming methods, and find stricter regulation does not generally reduce patenting. Patent signals support proactive wildlife-trade management.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Approach and data

Key findings

Implications for proactive management

Early warning of trends in commercial wildlife trade through novel machine-learning analysis of patent filing Hinsley, A.; Challender, D.W.S.; Masters, S.; Macdonald, D.W.; Milner-Gulland, E.J.; Fraser, J.; Wright, J. Citation Hinsley, A., Challender, D. W. S., Masters, S., Macdonald, D. W., Milner-Gulland, E. J., Fraser, J., & Wright, J. (2024) . Early warning of trends in commercial wildlife trade through novel machine-learning analysis of patent filing. Nature Communications, 15. doi:10.1038/s41467-024-49688-x Version: Publisher's Version License: Creative Commons CC BY 4.0 license Downloaded from: [https://hdl.handle.net/1887/4082942](https://hdl.handle.net/1887/4082942) Note: To cite this publication please use the final published version (if applicable) . Article [https://doi.org/10.1038/s41467-024-49688-x](https://doi.org/10.1038/s41467-024-49688-x) Early warning of trends in commercial wildlife trade through novel machinelearning analysis of patent ﬁling Received: 19 September 2023 | Accepted: 14 June 2024 | | --- | | | | Check for updates | A. Hinsley 1,2 , D. W. S. Challender1,2, S. Masters 3, D. W. Macdonald1, E. J. Milner-Gulland 1,2, J. Fraser 4,5 & J. Wright 2,6 Unsustainable wildlife trade imperils thousands of species, but efforts to identify and reduce these threats are hampered by rapidly evolving commercial markets. Businesses trading wildlife-derived products innovate to remain competitive, and the patents they ﬁle to protect their innovations also provide an early-warning of market shifts. Here, we develop a novel machine-learning approach to analyse patent-ﬁling trends and apply it to patents ﬁled from 1970-2020 related to six traded taxa that vary in trade legality, threat level, and use type: rhinoceroses, pangolins, bears, sturgeon, horseshoe crabs, and caterpillar fungus. We found 27,308 patents, showing 130% per-year increases, compared to a background rate of 104%. Innovation led to diversiﬁcation, including new fertilizer products using illegal-to-trade rhinoceros horn, and novel farming methods for pangolins. Stricter regulation did not generally correlate with reduced patenting. Patents reveal how wildlife-related businesses predict, adapt to, and create market shifts, providing data to underpin proactive wildlife-trade management approaches. The world is facing unprecedented rates of global biodiversity loss from threats including climate change, habitat loss and overexploitation1. To reverse this biodiversity crisis, and achieve the goals of the post-2020 Global Biodiversity Framework, there is an urgent need to move away from reactive conservation towards proactive, evidence-informed action1,2. Wildlife trade involves a diverse array of species3, and unsustainable trade has been linked to several hundred extinctions4, as well as large-scale declines in species such as pangolins harvested for the medicinal and meat trade5. Beyond biodiversity impacts, effective wildlife trade management is an increasingly important global priority6 due to links between wild animal markets and the origins of COVID-197,8, and wild animal welfare concerns in some markets, such as Asiatic black bears Ursus thibetanus farmed for their bile in Southeast Asia9. Adding further complexity, trade may also be essential to supporting livelihoods; in rural Nepal, harvesting of medicinal caterpillar fungus Ophiocordycepssinensis may contribute 65% of income in some areas10. Despite the importance of robust management, priorities for policy and action to manage trade are often identiﬁed based on historical legal or illegal trade data with little proactive foresight, despite some approaches offering critical insights into emerging wildlife trade trends11. However, wildlife markets are constantly changing as entrepreneurs commercialise new species or products, such as rare python colour morphs12, or expand markets for existing products, such as rebranding rhinoceros horn as a cancer treatment

FAQs

What problem does the study address in wildlife trade management?

Policy and action are often based on historical legal or illegal trade data with limited proactive foresight, while wildlife markets change rapidly due to new entrepreneurs, products, and regulatory events.

How does the research detect early warning signals?

It develops a machine-learning approach that analyzes patent-filing trends, using patents as a proxy for business innovation and market shifts.

What main patterns did the study find in patenting?

Across 1970–2020, the study found 27,308 patents, corresponding to 130% per-year increases versus a background rate of 104%, alongside innovation-driven diversification such as new rhinoceros horn-derived fertilizer products and pangolin farming methods.

Aug 5, 2026

Upload by Ivy