The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Real-time private consumption prediction using big data

빅데이터를 이용한 실시간 민간소비 예측

  • Received : 2023.05.19
  • Accepted : 2023.08.24
  • Published : 2024.02.29
Download PDF
⟨ Previous Next ⟩

Abstract

As economic uncertainties have increased recently due to COVID-19, there is a growing need to quickly grasp private consumption trends that directly reflect the economic situation of private economic entities. This study proposes a method of estimating private consumption in real-time by comprehensively utilizing big data as well as existing macroeconomic indicators. In particular, it is intended to improve the accuracy of private consumption estimation by comparing and analyzing various machine learning methods that are capable of fitting ultra-high-dimensional big data. As a result of the empirical analysis, it has been demonstrated that when the number of covariates including big data is large, variables can be selected in advance and used for model fit to improve private consumption prediction performance. In addition, as the inclusion of big data greatly improves the predictive performance of private consumption after COVID-19, the benefit of big data that reflects new information in a timely manner has been shown to increase when economic uncertainty is high.

최근 코로나19 등으로 경제 불확실성이 확대됨에 따라 민간 경제주체의 경제상황을 직접적으로 반영하는 민간소비 동향을 신속히 파악할 필요성이 높아지고 있다. 이에 본 연구는 기존 거시경제지표 뿐만 아니라 빅데이터를 종합적으로 활용하여 민간소비를 실시간으로 추정(nowcasting)하는 방법을 제안하였다. 특히 초고차원 빅데이터의 적합을 위해 활용 가능한 다양한 기계학습 방법론을 비교분석하여 민간소비 추정의 정확도를 향상시키고자 하였다. 실증 분석 결과, 빅데이터를 비롯한 가용 공변량의 수가 많은 경우에는 변수를 미리 선별하여 모형적합에 활용하는 것이 민간소비 예측 성능을 향상시킬 수 있음을 확인하였다. 또한 코로나19 이후 빅데이터의 반영이 민간소비 예측 성능을 더욱 크게 향상시킴에 따라 경제 불확실성이 높은 상황일수록 새로운 정보를 적시에 반영할 수 있는 고빈도 빅데이터의 활용가치가 높은 것으로 판단된다.

Keywords

Acknowledgement

본 연구는 한국은행의 연구용역지원을 받아 수행되었습니다.

References

  1. Aastveit KA, Fastbo, TM, Granziera E, Paulsen KS, and Torstensen KN (2020). Nowcasting norwegian household consumption with debit card transaction data, Norges Bank Working Paper, 2020, 1-33.
  2. Babii A, Ghysels E, and Striaukas J (2022). Machine learning time series regressions with an application to nowcasting, Journal of Business & Economic Statistics, 40, 1094-1106. https://doi.org/10.1080/07350015.2021.1899933
  3. Bajari P, Nekipelov D, Ryan SP, and Yang M (2015). Machine learning methods for demand estimation, American Economic Review, 105, 481-485. https://doi.org/10.1257/aer.p20151021
  4. Banbura M, Giannone D, Modugno M, and Reichlin L (2013). Now-casting and the real-time data flow, ' ECB Working Paper, 1564, 1-55.
  5. Barhoumi K, Darne O, and Ferrara L (2010). Are disaggregate data useful for factor analysis in forecasting ' French GDP?, Journal of Forecasting, 29, 132-144. https://doi.org/10.1002/for.1162
  6. Barnett W, Chauvet M, Leiva-Leon D, and Su L (2016). Nowcasting Nominal gdp with the Credit-card Augmented Divisia Monetary Aggregates, University of Kansas, Department of Economics, Lawrence, Kansas, 1-76.
  7. Breheny P and Huang J (2011). Coordinate descent algorithms for nonconvex penalized regression, with applications to biological feature selection, The Annals of Applied Statistics, 5, 232-253. https://doi.org/10.1214/10-AOAS388
  8. Chan JC and Jeliazkov I (2009). Efficient simulation and integrated likelihood estimation in state space models, International Journal of Mathematical Modelling and Numerical Optimisation, 1, 101-120. https://doi.org/10.1504/IJMMNO.2009.030090
  9. Chang J, Tang CY, and Wu Y (2013). Marginal empirical likelihood and sure independence feature screening, Annals of Statistics, 41, 2123-2148. https://doi.org/10.1214/13-AOS1139
  10. Chen B and Hood K (2020). Nowcasting of Advance Estimates of Personal Consumption of Services in the US National Accounts: Individual Versus Forecasting Combination Approach, BEA Working Paper, 2021, 1-37.
  11. Chen JC, Dunn A, Hood K, Driessen A, and Batch A (2019). Off to the races: A comparison of machine learning and alternative data for predicting economic indicators, In Katharine G. Abraham, Ron S. Jarmin, Brian Moyer, and Matthew D. Shapiro (Eds), Big Data for 21st Century Economic Statistics (pp. 373-402), University of Chicago Press, Chicago, USA.
  12. Chernis T and Sekkel R (2017). A dynamic factor model for nowcasting Canadian GDP growth, Empirical Economics, 53, 217-234. https://doi.org/10.1007/s00181-017-1254-1
  13. Delle Monache D and Petrella I (2019). Efficient matrix approach for classical inference in state space models, Economics Letters, 181, 22-27. https://doi.org/10.1016/j.econlet.2019.04.012
  14. Fan J, Feng Y, and Song R (2011). Nonparametric independence screening in sparse ultra-high-dimensional additive models, Journal of the American Statistical Association, 106, 544-557. https://doi.org/10.1198/jasa.2011.tm09779
  15. Fan J and Li R (2001). Variable selection via nonconcave penalized likelihood and its oracle properties, Journal of the American Statistical Association, 96, 1348-1360. https://doi.org/10.1198/016214501753382273
  16. Fan J and Lv J (2008). Sure independence screening for ultrahigh dimensional feature space, Journal of the Royal Statistical Society: Series B, 70, 849-911. https://doi.org/10.1111/j.1467-9868.2008.00674.x
  17. Fan J, Samworth R, and Wu Y (2009). Ultrahigh dimensional feature selection: Beyond the linear model, The Journal of Machine Learning Research, 10, 2013-2038.
  18. Galbraith JW and Tkacz G (2018). Nowcasting with payments system data, International Journal of Forecasting, 34, 366-376. https://doi.org/10.1016/j.ijforecast.2016.10.002
  19. Ghysels E, Santa-Clara P, and Valkanov R (2004). The MIDAS touch: Mixed data sampling regression models, UCLA: Finance, 2004, 1-32.
  20. Giannone D, Reichlin L, and Small D (2008). Nowcasting: The real-time informational content of macroeconomic data, Journal of Monetary Economics, 55, 665-676. https://doi.org/10.1016/j.jmoneco.2008.05.010
  21. Harvey AC (1990). Forecasting, Structural Time Series Models and the Kalman Filter, Cambridge University Press, Cambridge, UK.
  22. Hastie T, Tibshirani R, and Wainwright M (2015). Statistical Learning with Sparsity: The Lasso and Generalizations, CRC press, Boca Raton, FL.
  23. He X, Wang L, and Hong HG (2013). Quantile-adaptive model-free variable screening for high-dimensional heterogeneous data, The Annals of Statistics, 41, 342-369. https://doi.org/10.1214/13-AOS1087
  24. Kim C and Kim H (2016). Study on Nowcasting of GDP Growth Rates., BOK National Account Review, 2016, 1-23.
  25. Kim HH and Swanson NR (2018). Methods for backcasting, nowcasting and forecasting using factor-MIDAS: With an application to Korean GDP, Journal of Forecasting, 37, 281-302. https://doi.org/10.1002/for.2499
  26. Koenker R and Hallock KF (2001). Quantile regression, Journal of Economic Perspectives, 15, 143-156. https://doi.org/10.1257/jep.15.4.143
  27. Lee K and Hwang S (2016). Development of economic indicators using big data: Creation of Naver search economic index and review of its usefulness, BOK Economic Analysis, 20, 1-38.
  28. Lee H, Choi D, Kim Y, and Huh J (2022). Development of a real-time economic forecast system for the current quarter (GDP nowcasting) using digital new technologies, BOK Issue Note, 2022.
  29. Li B (2018). Sufficient Dimension Reduction: Methods and Applications with R, Chapman and Hall/CRC, Boca Raton, FL.
  30. Li R, Zhong W, and Zhu L (2012). Feature screening via distance correlation learning, Journal of the American Statistical Association, 107, 1129-1139. https://doi.org/10.1080/01621459.2012.695654
  31. Li Y, Liu Y, and Zhu J (2007). Quantile regression in reproducing kernel Hilbert spaces, Journal of the American Statistical Association, 102, 255-268. https://doi.org/10.1198/016214506000000979
  32. Lin Y and Zhang HH (2006). Component selection and smoothing in multivariate nonparametric regression, The Annals of Statistics, 34, 2272-2297. https://doi.org/10.1214/009053606000000722
  33. Luciani M and Ricci L (2013). Nowcasting norway, International Journal of Central Banking, 10, 215-248. https://doi.org/10.2139/ssrn.2211647
  34. Marcellino M and Schumacher C (2010). Factor MIDAS for nowcasting and forecasting with ragged-edge data: A model comparison for German GDP, Oxford Bulletin of Economics and Statistics, 72, 518-550. https://doi.org/10.1111/j.1468-0084.2010.00591.x
  35. Matheson TD (2010). An analysis of the informational content of New Zealand data releases: The importance of business opinion surveys, Economic Modelling, 27, 304-314. https://doi.org/10.1016/j.econmod.2009.09.010
  36. Moriwaki D (2019). Nowcasting unemployment rates with smartphone GPS data, In Chiara Renso, Stan Matwin, Konstantinos Tserpes (Eds), International Workshop on Multiple-Aspect Analysis of Semantic Trajectories (pp. 21-33), Springer, Wurzburg, Germany.
  37. Raju S and Balakrishnan M (2019). Nowcasting economic activity in India using payment systems data, Journal of Payments Strategy & Systems, 13, 72-81.
  38. Richardson A, Mulder T, and Vehbi T (2019). Nowcasting New Zealand GDP using machine learning algorithms, IFC Bulletins chapters in Bank for International Settlements, 50, 1-15, Available from: https://ideas.repec.org/h/bis/bisifc/50-15.html
  39. Seo J (2017). Study on the feasibility of using credit card information for estimating domestic household income and consumption expenditure, Journal of The Korean Data Analysis Society, 19, 403-412. https://doi.org/10.37727/jkdas.2017.19.1.403
  40. Tibshirani R (1996). Regression shrinkage and selection via the lasso, Journal of the Royal Statistical Society: Series B (Methodological), 58, 267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
  41. Zhang T (2002). Covering number bounds of certain regularized linear function classes, Journal of Machine Learning Research, 2, 527-550.
  42. Zhu LP, Li L, Li R, and Zhu LX (2011). Model-free feature screening for ultrahigh-dimensional data, Journal of the American Statistical Association, 106, 1464-1475. https://doi.org/10.1198/jasa.2011.tm10563
  43. Zou H and Hastie T (2005). Regularization and variable selection via the elastic net, Journal of the Royal Statistical Society: Series B (Statistical Methodology), 67, 301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x