Identifying Business Cycle Turning Points in Real Time

We propose a simple machine-learning algorithm known as Learning Vector Quantization (LVQ) for the purpose of identifying new U.S. business cycle turning points quickly in real time. LVQ is used widely for real-time statistical classification in many other fields, but has not previously been applied to the classification of economic variables, to the best of our knowledge. The algorithm is intuitive and simple to implement, and easily incorporates salient features of the real-time nowcasting environment, such as differences in data reporting lags across series. We evaluate the algorithm’s real-time ability to establish new business cycle turning points in the United States quickly and accurately over the past five NBER recessions. Despite its relative simplicity, the algorithm’s performance appears to be very competitive with those of commonly used alternatives.

[1]  P. Spindt,et al.  The Micromechanics of the Federal Funds Market: Implications for Day-of-the-Week Effects in Funds Rate Variability , 1988, Journal of Financial and Quantitative Analysis.

[2]  Travis J. Berge.  Predicting Recessions with Leading Indicators: Model Averaging and Selection over the Business Cycle: Predicting Recessions with Leading Indicators , 2015 .

[3]  Francis X. Diebold,et al.  Real-Time Measurement of Business Conditions , 2007 .

[4]  James D. Hamilton.  The Daily Market for Federal Funds , 1996, Journal of Political Economy.

[5]  Chang-Jin Kim,et al.  Nonlinearity and the permanent effects of recessions , 2002 .

[6]  Monica Hargraves,et al.  A Historical Assessment of the Rationales and Functions of Reserve Requirements , 1983 .

[7]  Myung-Jig Kim,et al.  New index of coincident indicators: A multivariate Markov switching factor model approach , 1995 .

[8]  D. Thornton.  The borrowed-reserves operating procedures: theory and evidence , 1988 .

[9]  Kevin L. Kliesen,et al.  Unemployment insurance claims and economic activity , 2002 .

[10]  Peggy E. Swanson.  The international transmission of interest rates: A note on causal relationships between short-term external and domestic U.S. dollar returns , 1988 .

[11]  Oscar Jorda,et al.  Evaluating the Classification of Economic Activity into Recessions and Expansions , 2011 .

[12]  Sebastian Fossati,et al.  Dating US business cycles with macro factors , 2016 .

[13]  Mark D. Griffiths,et al.  Day-of-the-week effects in federal funds rates: Further empirical findings , 1995 .

[14]  Serena Ng.  Viewpoint: Boosting Recessions (Prévoir les Recessions) , 2014 .

[15]  James D. Hamilton,et al.  Dating Business Cycle Turning Points , 2005 .

[16]  Oscar Jorda,et al.  The Classification of Economic Activity , 2009 .

[17]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[18]  L. Hurwicz,et al.  Measuring Business Cycles. , 1946 .

[19]  Travis J. Berge,et al.  The Classification of Economic Activity into Expansions and Recessions , 2009 .

[20]  Daniel B. Nelson.  CONDITIONAL HETEROSKEDASTICITY IN ASSET RETURNS: A NEW APPROACH , 1991 .

[21]  Mark W. Watson,et al.  Indicators for Dating Business Cycles: Cross-History Selection and Comparisons , 2010 .

[22]  Marcelle Chauvet,et al.  An Econometric Characterization of Business Cycle Dynamics with Factor Structure and Regime Switching , 1998 .

[23]  Serena Ng.  BOOSTING RECESSIONS , 2013 .

[24]  Milton Friedman,et al.  THE “PLUCKING MODEL” OF BUSINESS FLUCTUATIONS REVISITED , 1993 .

[25]  Margaret Mary McConnell.  Rethinking the Value of Initial Claims as a Forecasting Tool , 1998 .

[26]  Travis J. Berge.  Predicting Recessions with Leading Indicators: Model Averaging and Selection Over the Business Cycle , 2014 .

[27]  J. Wooldridge,et al.  Quasi-maximum likelihood estimation and inference in dynamic models with time-varying covariances , 1992 .

[28]  Chang‐Jin Kim,et al.  State-Space Models with Regime-Switching: Classical and Gibbs Sampling Approaches with Applications , 1999 .

[29]  James D. Hamilton.  A New Approach to the Economic Analysis of Nonstationary Time Series and the Business Cycle , 1989 .

[30]  Daniel E. Sichel.  Inventories and the three phases of the business cycle , 1994 .

[31]  Maximo Camacho,et al.  Markov-Switching Dynamic Factor Models in Real Time , 2012, International Journal of Forecasting.

[32]  John Wagster,et al.  The Causality Effects of the Federal Reserve's Monetary Policy on U.S. and Eurodollar Interest Rates , 1997 .

[33]  Adrian Pagan,et al.  Synchronization of cycles , 2006 .

[34]  Glenn D. Rudebusch,et al.  Forecasting Recessions: The Puzzle of the Enduring Power of the Yield Curve , 2007 .

[35]  Pentti Saikkonen,et al.  Predicting U.S. Recessions with Dynamic Binary Response Models , 2008, The Review of Economics and Statistics.

[36]  Marcelle Chauvet,et al.  Forecasting Recessions Using the Yield Curve , 2001 .

[37]  K. P. Vishwakarma,et al.  Recognizing business cycle turning points by means of a neural network , 1994 .

[38]  Jonathan H. Wright,et al.  Forecasting Inflation , 2011 .

[39]  James D. Hamilton.  Calling Recessions in Real Time , 2010 .

[40]  Hung-Gay Fung,et al.  The international transmission of eurodollar and US interest rates: A cointegration analysis , 1992 .

[41]  Marcelle Chauvet,et al.  A Comparison of the Real-Time Performance of Business Cycle Dating Methods , 2005 .

[42]  Sydney C. Ludvigson,et al.  Macro Factors in Bond Risk Premia , 2005 .

[43]  Bruce E. Hansen,et al.  Erratum: The likelihood ratio test under nonstandard conditions: Testing the Markov switching model of GNP , 1996 .

[44]  L. Glosten,et al.  On the Relation between the Expected Value and the Volatility of the Nominal Excess Return on Stocks , 1993 .

[45]  Alex Kane,et al.  Measuring Risk Aversion from Excess Returns on a Stock Index , 1991 .

[46]  Chang-Jin Kim,et al.  Friedman's Plucking Model of Business Fluctuations: Tests and Estimates of Permanent and Transitory Components , 1998 .

[47]  M. Qi.  Predicting US recessions with leading indicators via neural network models , 2001 .

[48]  S. Chib,et al.  Bayes inference via Gibbs sampling of autoregressive time series subject to Markov mean and variance shifts , 1993 .

[49]  H. Fushing,et al.  A Chronology of International Business Cycles Through Non-Parametric Decoding , 2010 .

[50]  Analysis of Federal Funds Rate Changes and Variance Patterns , 2001 .

[51]  Dean Croushore,et al.  A real-time data set for macroeconomists , 2001 .

[52]  G. H. Moore,et al.  Appendix A: The Development and Role of the National Bureau of Economic Research's Business Cycle Chronologies , 1986 .

[53]  Atsushi Sato,et al.  Generalized Learning Vector Quantization , 1995, NIPS.

[54]  Michael D. Boldin,et al.  Dating Turning Points in the Business Cycle , 1994 .

[55]  Allan P. Layton,et al.  Dating and predicting phase changes in the U.S. business cycle , 1996 .

[56]  Thomas Villmann,et al.  Generalized relevance learning vector quantization , 2002, Neural Networks.

[57]  Gary Koop,et al.  Do recessions permanently change output , 1993 .

[58]  Mark W. Watson,et al.  Estimating Turning Points Using Large Data Sets , 2010 .

[59]  J. Feinman.  Reserve requirements: history, current practice, and potential reform , 1993 .