Early identification of emerging technologies: A machine learning approach using multiple patent indicators

Patent citation analysis is considered a useful tool for identifying emerging technologies. However, the outcomes of previous methods are likely to reveal no more than current key technologies, since they can only be performed at later stages of technology development due to the time required for patents to be cited (or fail to be cited). This study proposes a machine learning approach to identifying emerging technologies at early stages using multiple patent indicators that can be defined immediately after the relevant patents are issued. For this, first, a total of 18 input and 3 output indicators are extracted from the United States Patent and Trademark Office database. Second, a feed-forward multilayer neural network is employed to capture the complex nonlinear relationships between input and output indicators in a time period of interest. Finally, two quantitative indicators are developed to identify trends of a technology's emergingness over time. Based on this, we also provide the practical guidelines for implementation of the proposed approach. The case of pharmaceutical technology shows that our approach can facilitate responsive technology forecasting and planning.

[1]  A. Fernandez-Ribas.  International Patent Strategies of Small and Large Firms: An Empirical Study of Nanotechnology , 2010 .

[2]  Michel Callon,et al.  The state and technical innovation: a case study of the electrical vehicle in France☆ , 1980 .

[3]  S. Chaudhuri,et al.  The WTO and India's Pharmaceuticals Industry: Patent Protection, TRIPS, and Developing Countries , 2005 .

[4]  A. A. Kayal,et al.  An empirical evaluation of the technology cycle time indicator as a measure of the pace of technological progress in superconductor technology , 1999 .

[5]  Jean-Michel Poggi,et al.  Variable selection using random forests , 2010, Pattern Recognit. Lett..

[6]  Holger Ernst,et al.  Patent information for strategic technology management , 2003 .

[7]  Kwangsoo Kim,et al.  Monitoring emerging technologies for technology planning using technical keyword based analysis from patent data , 2017 .

[8]  Bart Verspagen,et al.  Does it matter where patent citations come from? Inventor versus examiner citations in European patents , 2005 .

[9]  D. Harhoff,et al.  Citation Frequency and the Value of Patented Inventions , 1999, Review of Economics and Statistics.

[10]  Soung Hie Kim,et al.  A qualitative cross-impact approach to find the key technology , 1997 .

[11]  Wei-Der Chang,et al.  A feedforward neural network with function shape autotuning , 1996, Neural Networks.

[12]  William J. Abernathy,et al.  Patterns of Industrial Innovation , 1978 .

[13]  Z. Griliches,et al.  Citations, Family Size, Opposition and the Value of Patent Rights Have Profited from Comments and Suggestions , 2002 .

[14]  Hsin-Yu Shih,et al.  Patent citation network analysis of core and emerging technologies in Taiwan: 1997–2008 , 2011, Scientometrics.

[15]  P. Bierly,et al.  Determinants of technology cycle time in the U.S. pharmaceutical industry , 1996 .

[16]  B. Martin.  Foresight in science and technology , 1995 .

[17]  Stephen A. Billings,et al.  Non-linear system identification using neural networks , 1990 .

[18]  Bart Verspagen,et al.  Technology Spillovers between Sectors and over Time. , 1999 .

[19]  Koenraad Debackere,et al.  Traces of Prior Art: An analysis of non-patent references found in patent documents , 2006, Scientometrics.

[20]  Lee Fleming,et al.  Special Issue on Design and Development: Recombinant Uncertainty in Technological Search , 2001, Manag. Sci..

[21]  Martin G. Moehrle,et al.  A new instrument for technology monitoring: novelty in patents measured by semantic patent analysis , 2012, Scientometrics.

[22]  Changyong Lee,et al.  Hawkes process-based technology impact analysis , 2017, J. Informetrics.

[23]  Russell G. Death,et al.  An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data , 2004 .

[24]  M.M.S. Karki,et al.  Patent citation analysis: A policy analysis tool , 1997 .

[25]  James Bessen.  The Value of U.S. Patents by Owner and Patent Characteristics , 2006 .

[26]  Manuel Trajtenberg,et al.  Economic Analysis of Product Innovation: The Case of CT Scanners , 1990 .

[27]  Manuel Trajtenberg,et al.  Patents, Citations, and Innovations: A Window on the Knowledge Economy , 2002 .

[28]  Tugrul U. Daim,et al.  Forecasting emerging technologies: Use of bibliometrics and patent analysis , 2006 .

[29]  Alan L. Porter,et al.  Capturing new developments in an emerging technology: an updated search strategy for identifying nanotechnology research outputs , 2013, Scientometrics.

[30]  B. Yegnanarayana,et al.  Artificial Neural Networks , 2004 .

[31]  M. Lange,et al.  Patent indicators for the technology life cycle development , 2007 .

[32]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[33]  So Young Sohn,et al.  Patent-based QFD framework development for identification of emerging technologies and related business models: A case of robot technology in Korea , 2015 .

[34]  Jürgen Bode,et al.  Decision support with neural networks in the management of research and development: Concepts and application to cost estimation , 1998, Inf. Manag..

[35]  Oh-Jin Kwon,et al.  Concentric diversification based on technological capabilities: Link analysis of products and technologies , 2017 .

[36]  Changyong Lee,et al.  Robust Future‐Oriented Technology Portfolios: Black–Litterman Approach , 2013 .

[37]  Yu-Shan Chen,et al.  Utilizing patent analysis to explore the cooperative competition relationship of the two LED companies: Nichia and Osram , 2011 .

[38]  Massimo Buscema,et al.  What kind of ‘world order’? An artificial neural networks approach to intensive data mining , 2017 .

[39]  Yongtae Park,et al.  How to assess patent infringement risks: a semantic patent claim analysis using dependency relationships , 2013, Technol. Anal. Strateg. Manag..

[40]  Calvin S. Weng,et al.  A New Comprehensive Patent Analysis Approach for New Product Design in Mechanical Engineering , 2011 .

[41]  Bruno van Pottelsberghe de la Potterie,et al.  Applications, grants and the value of patent , 2000 .

[42]  M. Gittelman,et al.  Applicant and Examiner Citations in US Patents: An Overview and Analysis , 2008 .

[43]  Milton S. Boyd,et al.  Designing a neural network for forecasting financial and economic time series , 1996, Neurocomputing.

[44]  Alan L. Porter,et al.  Emerging technologies: quantitative identification and measurement , 2010, Technol. Anal. Strateg. Manag..

[45]  Melissa A. Schilling,et al.  Mapping the Technological Landscape: Measuring Technology Distance, Technological Footprints, and Technology Evolution , 2016 .

[46]  Finn V. Jensen,et al.  Bayesian Networks and Decision Graphs , 2001, Statistics for Engineering and Information Science.

[47]  Sungjoo Lee,et al.  Technological Forecasting & Social Change Business planning based on technological capabilities : Patent analysis for technology-driven roadmapping ☆ , 2009 .

[48]  Changyong Lee,et al.  Patterns of technology life cycles: stochastic analysis based on patent citations , 2017, Technol. Anal. Strateg. Manag..

[49]  Oh-Jin Kwon,et al.  Stochastic technology life cycle analysis using multiple patent indicators , 2016 .

[50]  Daniele Rotolo,et al.  Emerging Technology , 2001 .

[51]  Anthony Breitzman,et al.  The Emerging Clusters Model: A tool for identifying emerging technologies across multiple patent systems , 2015 .

[52]  Martin Meyer,et al.  Are patenting scientists the better scholars?: An exploratory comparison of inventor-authors with their non-inventing peers in nano-science and technology , 2006 .

[53]  Yu-Shan Chen,et al.  Nonlinear influence on R&D project performance , 2012 .

[54]  Bart Van Looy,et al.  Delineating the scientific footprint in technology: Identifying scientific publications within non-patent references , 2011, Scientometrics.

[55]  Sungjoo Lee,et al.  Technology clustering based on evolutionary patterns: The case of information and communications technologies☆ , 2011 .

[56]  M. Gevrey,et al.  Review and comparison of methods to study the contribution of variables in artificial neural network models , 2003 .

[57]  George S. Day,et al.  Avoiding the Pitfalls of Emerging Technologies , 2000 .

[58]  Inchae Park,et al.  Forecasting technology substitution based on hazard function , 2016 .

[59]  Yu-Shan Chen,et al.  The relationship between a firm's patent quality and its market value — The case of US pharmaceutical industry , 2010 .

[60]  Nils C. Newman,et al.  Measuring national ‘emerging technology’ capabilities , 2002 .

[61]  J. Dayhoff,et al.  Artificial neural networks , 2001, Cancer.

[62]  Zhenzhong Ma,et al.  Patent application and technological collaboration in inventive activities: 1980–2005 , 2008 .

[63]  Bokyoung Kang,et al.  Novelty-focused patent mapping for technology opportunity analysis , 2015 .

[64]  H. Small,et al.  Identifying emerging topics in science and technology , 2014 .

[65]  Thorsten Teichert,et al.  Inventive progress measured by multi-stage patent citation analysis , 2005 .

[66]  Kwangsoo Kim,et al.  Identifying rapidly evolving technological trends for R&D planning using SAO-based semantic patent networks , 2011, Scientometrics.

[67]  Mark A. Schankerman,et al.  Characteristics of patent litigation: a window on competition , 2001 .

[68]  J. Lerner.  The Importance of Patent Scope: An Empirical Analysis , 1994 .

[69]  Yangrae Cho,et al.  A stochastic patent citation analysis approach to assessing future technological impacts , 2012 .

[70]  F. Narin,et al.  Patents as indicators of corporate technological strength , 1987 .