The Knowledge Graph for Macroeconomic Analysis with Alternative Big Data

The current knowledge system of macroeconomics is built on interactions among a small number of variables, since traditional macroeconomic models can mostly handle a handful of inputs. Recent work using big data suggests that a much larger number of variables are active in driving the dynamics of the aggregate economy. In this paper, we introduce a knowledge graph (KG) that consists of not only linkages between traditional economic variables but also new alternative big data variables. We extract these new variables and the linkages by applying advanced natural language processing (NLP) tools on the massive textual data of academic literature and research reports. As one example of the potential applications, we use it as the prior knowledge to select variables for economic forecasting models in macroeconomics. Compared to statistical variable selection methods, KG-based methods achieve significantly higher forecasting accuracy, especially for long run forecasts.

[1]  Paul Newbold,et al.  Testing the equality of prediction mean squared errors , 1997 .

[2]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[3]  Jianqing Fan,et al.  Recent Developments in Factor Models and Applications in Econometric Learning , 2020, Annual Review of Financial Economics.

[4]  Christopher D. Manning,et al.  Improved Pattern Learning for Bootstrapped Entity Extraction , 2014, CoNLL.

[5]  Daniel S. Weld,et al.  Fine-Grained Entity Recognition , 2012, AAAI.

[6]  Maxime Leroux,et al.  How is Machine Learning Useful for Macroeconomic Forecasting? , 2019, Journal of Applied Econometrics.

[7]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[8]  Lawrence J. Christiano,et al.  Nominal Rigidities and the Dynamic Effects of a Shock to Monetary Policy , 2001, Journal of Political Economy.

[9]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[10]  Zhi-Hua Zhou,et al.  A brief introduction to weakly supervised learning , 2018 .

[11]  David H. Small,et al.  Nowcasting: the real time informational content of macroeconomic data releases , 2008 .

[12]  C. Sims.  Money, Income, and Causality , 1972 .

[13]  R. Shiller.  Narrative Economics , 2017 .

[14]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[15]  Serena Ng,et al.  Working Paper Series , 2019 .

[16]  Philip S. Yu,et al.  A Survey on Knowledge Graphs: Representation, Acquisition and Applications , 2020, ArXiv.

[17]  Jianqing Fan,et al.  Factor-Adjusted Regularized Model Selection , 2016, Journal of econometrics.

[18]  F. Diebold,et al.  Comparing Predictive Accuracy , 1994, Business Cycles.

[19]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[20]  Yoram Singer,et al.  Unsupervised Models for Named Entity Classification , 1999, EMNLP.

[21]  Frank Smets,et al.  Shocks and Frictions in Us Business Cycles: A Bayesian DSGE Approach , 2007, SSRN Electronic Journal.

[22]  Mari Ostendorf,et al.  Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction , 2018, EMNLP.

[23]  H. Zou,et al.  Addendum: Regularization and variable selection via the elastic net , 2005 .

[24]  Robert B. Litterman,et al.  Forecasting and Conditional Projection Using Realistic Prior Distributions , 1983 .

[25]  Mark W. Watson,et al.  Dynamic Factor Models, Factor-Augmented Vector Autoregressions, and Structural Vector Autoregressions in Macroeconomics , 2016 .

[26]  T. Zha,et al.  Forecasting China's Economic Growth and Inflation , 2016 .

[27]  Steffen Staab,et al.  Knowledge graphs , 2020, Commun. ACM.

[28]  C. Sims,et al.  Bayesian methods for dynamic multivariate models , 1998 .