Machine-learned patterns suggest that diversification drives economic development

We combine a sequence of machine-learning techniques, together called Principal Smooth-Dynamics Analysis (PriSDA), to identify patterns in the dynamics of complex systems. Here, we deploy this method on the task of automating the development of new theory of economic growth. Traditionally, economic growth is modelled with a few aggregate quantities derived from simplified theoretical models. PriSDA, by contrast, identifies important quantities. Applied to 55 years of data on countries’ exports, PriSDA finds that what most distinguishes countries’ export baskets is their diversity, with extra weight assigned to more sophisticated products. The weights are consistent with previous measures of product complexity. The second dimension of variation is proficiency in machinery relative to agriculture. PriSDA then infers the dynamics of these two quantities and of per capita income. The inferred model predicts that diversification drives growth in income, that diversified middle-income countries will grow the fastest, and that countries will converge onto intermediate levels of income and specialization. PriSDA is generalizable and may illuminate dynamics of elusive quantities such as diversity and complexity in other natural and social systems.

[1]  M. Rosenzweig,et al.  Species Diversity in Space and Time , 1995 .

[2]  Danny Quah,et al.  Empirical cross-section dynamics in economic growth , 1993 .

[3]  Steven L. Brunton,et al.  Inferring Biological Networks by Sparse Identification of Nonlinear Dynamics , 2016, IEEE Transactions on Molecular, Biological and Multi-Scale Communications.

[4]  César A. Hidalgo,et al.  The network structure of economic output , 2011, 1101.1707.

[5]  Mansour Alsaleh,et al.  729 new measures of economic complexity (Addendum to Improving the Economic Complexity Index) , 2017 .

[6]  César A. Hidalgo,et al.  The Product Space Conditions the Development of Nations , 2007, Science.

[7]  Costas Arkolakis,et al.  New Trade Models, Same Old Gains? , 2009 .

[8]  G. Caldarelli,et al.  Economic complexity: Conceptual grounding of a new metrics for global competitiveness , 2013 .

[9]  西口 清勝,et al.  The East Asian Miracle--Economic Growth and Public Policy/World Bank(1993) , 1993 .

[10]  J. Bai,et al.  Forecasting economic time series using targeted predictors , 2008 .

[11]  Bryan C. Daniels,et al.  Automated adaptive inference of phenomenological dynamical models , 2015, Nature Communications.

[12]  Alan Y. Chiang,et al.  Generalized Additive Models: An Introduction With R , 2007, Technometrics.

[13]  S. Alkire,et al.  Counting and Multidimensional Poverty Measurement , 2010 .

[14]  Michele Caraglio,et al.  Export dynamics as an optimal growth problem in the network of global economy , 2016, Scientific Reports.

[15]  Luciano Pietronero,et al.  The Heterogeneous Dynamics of Economic Complexity , 2015, PloS one.

[16]  Mansour Alsaleh,et al.  Improving the Economic Complexity Index , 2017 .

[17]  Michael J. Ferrantino,et al.  Accounting for Discrepancies in Bilateral Trade: The Case of China, Hong Kong, and the United States , 2007 .

[18]  Daniel Servén,et al.  pyGAM: Generalized Additive Models in Python , 2018 .

[19]  J. Stachurski,et al.  A Forward Projection of the Cross-Country Income Distribution , 2003 .

[20]  D. Hruschka,et al.  Material wealth in 3 D : Mapping multiple paths to prosperity in low-and middle-income countries , 2022 .

[21]  Guido Caldarelli,et al.  Measuring the Intangibles: A Metrics for the Economic Complexity of Countries and Products , 2013, PloS one.

[22]  M. Ferrantino,et al.  Evasion Behaviors of Exporters and Importers: Evidence from the U.S.–China Trade Data Discrepancy , 2012 .

[23]  J. Eaton,et al.  Putting Ricardo to Work , 2012 .

[24]  Guido Caldarelli,et al.  A New Metrics for Countries' Fitness and Products' Complexity , 2012, Scientific Reports.

[25]  Jason Hwang,et al.  What you export matters , 2005 .

[26]  Samuel M. Otterstrom,et al.  Exploring the accuracy of international trade statistics , 1998 .

[27]  A. Yeats On the Accuracy of Partner Country Trade Statistics , 2009 .

[28]  Eric A. Hanushek,et al.  Do better schools lead to more growth? Cognitive skills, economic outcomes, and causation , 2009, SSRN Electronic Journal.

[29]  Steven L. Brunton,et al.  Data-driven discovery of partial differential equations , 2016, Science Advances.

[30]  Edsel L. Beja Estimating Trade Mis-Invoicing from China: 2000-2005 , 2008 .

[31]  Monica Matei-Chesnoiu Geography and Trade , 2012 .

[32]  A. Yeats On the accuracy of economic observations : do sub-Saharan trade statistics mean anything? , 1990 .

[33]  Patrick Clawson,et al.  The East Asian miracle: Economic growth and public policy: By the World Bank. (New York: Oxford University Press for the World Bank, 1993. 389 pp. $19.95, paper.) , 1995 .

[34]  John Baines,et al.  Quantitative historical analysis uncovers a single dimension of complexity that structures global variation in human social organization , 2017, Proceedings of the National Academy of Sciences.

[35]  Hod Lipson,et al.  Distilling Free-Form Natural Laws from Experimental Data , 2009, Science.

[36]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[37]  Katherine Barbieri,et al.  Trading Data , 2009 .

[38]  Michele Caraglio,et al.  Growth dynamics and complexity of national economies in the global trade network , 2018, Scientific Reports.

[39]  Gwilym M. Jenkins,et al.  Time series analysis, forecasting and control , 1971 .

[40]  Hod Lipson,et al.  Automated reverse engineering of nonlinear dynamical systems , 2007, Proceedings of the National Academy of Sciences.

[41]  J. Bhagwati ON THE UNDERINVOICING OF IMPORTS1 , 2009 .

[42]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[43]  Long Zhang,et al.  Forward and backward least angle regression for nonlinear system identification , 2015, Autom..

[44]  Steward T. A. Pickett,et al.  The Ecology of Natural Disturbance and Patch Dynamics , 1985 .

[45]  Steven L. Brunton,et al.  Sparse Identification of Nonlinear Dynamics with Control (SINDYc) , 2016, 1605.06682.

[46]  C. I. Jones,et al.  The New Kaldor Facts: Ideas, Institutions, Population, and Human Capital , 2009 .

[47]  César A. Hidalgo,et al.  The Atlas of Economic Complexity: Mapping Paths to Prosperity , 2011 .

[48]  Mark J. Gehlhar,et al.  Reconciling Bilateral Trade Data for Use in GTAP , 2000, GTAP Technical Paper Series.

[49]  Andrea Tacchella,et al.  A dynamical systems approach to gross domestic product forecasting , 2018, Nature Physics.

[50]  S. Brunton,et al.  Discovering governing equations from data by sparse identification of nonlinear dynamical systems , 2015, Proceedings of the National Academy of Sciences.

[51]  Naomi S. Altman,et al.  Points of Significance: Principal component analysis , 2017, Nature Methods.

[52]  Danny Quah,et al.  Convergence empirics across economies with (some) capital mobility , 1996 .

[53]  D. Hruschka,et al.  Material wealth in 3D: Mapping multiple paths to prosperity in low- and middle- income countries , 2017, PloS one.

[54]  Johannes Gehrke,et al.  Sparse Partially Linear Additive Models , 2014, ArXiv.

[55]  B. Balassa Trade Liberalisation and “Revealed” Comparative Advantage , 1965 .

[56]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[57]  J N Kutz,et al.  Model selection for dynamical systems via sparse regression and information criteria , 2017, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[58]  S. Wood Fast stable restricted maximum likelihood and marginal likelihood estimation of semiparametric generalized linear models , 2011 .

[59]  J.A. Tenreiro Machado,et al.  Analysis of World Economic Variables Using Multidimensional Scaling , 2014, PloS one.

[60]  A. Yeats,et al.  On the (in)accuracy of economic observations: An assessment of trends in the reliability of international trade statistics , 1994 .

[61]  Seiji Naya,et al.  The Accuracy of International Trade Data: The Case of Southeast Asian Countries , 1969 .

[62]  G. Gaulier,et al.  BACI: International Trade Database at the Product-Level (the 1994-2007 Version) , 2009 .

[63]  Johannes Gehrke,et al.  Accurate intelligible models with pairwise interactions , 2013, KDD.

[64]  César A. Hidalgo,et al.  The building blocks of economic complexity , 2009, Proceedings of the National Academy of Sciences.

[65]  I. Jolliffe Principal Component Analysis , 2002 .

[66]  T. Hastie,et al.  Generalized Additive Model Selection , 2015, 1506.03850.

[67]  S. Wood Generalized Additive Models: An Introduction with R , 2006 .

[68]  Paul Voosen,et al.  How AI detectives are cracking open the black box of deep learning , 2017 .