Leveraging machine learning for Australian macroeconomic forecasting

Abstract

Macroeconomic forecasting has traditionally relied on regression and time series methods, which have often struggled to outperform basic benchmarks. In this study, we explore the use of machine learning (ML) and deep learning (DL) techniques to forecast key macroeconomic indicators for Australia, specifically focusing on Gross Domestic Product growth, Consumer Price Index inflation, and the Interbank Overnight Cash Rate. Using a comprehensive dataset spanning from 1985 to 2023, we incorporate 16 predictors identified from previous literature. Our findings indicate that ML methods, particularly ensemble approaches such as Random Forest and XGBoost, deliver superior predictive performance compared to traditional time series models and \textsc{dl} methods. Although DL models such as Long Short-Term Memory (LSTM) and Convolutional Neural Network-LSTM were also tested, they did not achieve comparable accuracy in this context, highlighting the effectiveness of density-based ML approaches for macroeconomic forecasting.

References

• F. R. Alharbi and D. Csala. A seasonal autoregressive integrated moving average with exogenous factors (SARIMAX) forecasting model-based time series approach. Intentions 7.4 (2022), p. 94. doi: 10.3390/inventions7040094
• A. Alsharef, K. Aggarwal, Sonia, M. Kumar, and A. Mishra. Review of ML and AutoML solutions to forecast time-series data. Arc. Comput. Meth. Eng. 29.7 (2022), pp. 5297–5311. doi: 10.1007/s11831-022-09765-0
• R. Ashley. On the usefulness of macroeconomic forecasts as inputs to forecasting models. J. Forecast. 2.3 (1983), pp. 211–223. doi: 10.1002/for.3980020304
• D. Brezak, T. Bacek, D. Majetic, J. Kasac, and B. Novakovic. A Comparison of Feed-Forward and Recurrent Neural Networks in Time Series Forecasting. IEEE Conf. Comput. Intel. Fin. Eng. Econ. (2012), pp. 1–6. doi: 10.1109/CIFEr.2012.6327793
• T. Chu and F. Qureshi. Comparing out-of-sample performance of machine learning methods to forecast U.S. GDP growth. Comput. Econ. 62 (2022), pp. 1567–1609. doi: 10.1007/s10614-022-10312-z
• Wind Info Co. Wind Financial. 2024. url: https://www.wind.com.cn/
• A. D’Agostino, L. Gambetti, and D. Giannone. Macroeconomic forecasting and structural change. J. Appl. Econ. 28 (2011), pp. 82–101. doi: 10.1002/jae.1257
• S. Demir and E. K. Sahin. An investigation of feature selection methods for soil liquefaction prediction based on tree-based ensemble algorithms using AdaBoost, gradient boosting, and XGBoost. Neur. Comput. Appl. 35.4 (2023), pp. 3173–3190. doi: 10.1007/s00521-022-07856-4
• F. X. Diebold. The past, present, and future of macroeconomic forecasting. J. Econ. Perspect. 12.2 (1998), pp. 175–192. doi: 10.1257/jep.12.2.175
• R. Fildes. Quantitative forecasting—the state of the art: Econometric models. J. Op. Res. Soc. 36.7 (1985), pp. 549–580. doi: 10.2307/2582473
• R. Fildes and H. Stekler. The state of macroeconomic forecasting. J. Macroecon. 24.4 (2002), pp. 435–468. doi: 10.1016/s0164-0704(02)00055-1
• H. Ghoddusi, G. G. Creamer, and N. Rafizadeh. Machine learning in energy economics and finance: A review. Energy Econ. 81 (2019), pp. 709–727. doi: 10.1016/j.eneco.2019.05.006
• D. Giannone, M. Lenza, and G. E. Primiceri. Economic predictions with big data: The illusion of sparsity. Econometrica 89.5 (2021), pp. 2409–2437. doi: 10.3982/ECTA17842
• U. Heilemann and H. Stekler. Introduction to The future of macroeconomic forecasting. Int. J. Forecast. 23.2 (2007), pp. 159–165. doi: 10.1016/j.ijforecast.2007.01.001 p. C169).
• D. F. Hendry. The econometrics of macroeconomic forecasting. Econ. J. 107.444 (1997), pp. 1330–1357. doi: 10.1111/j.1468-0297.1997.tb00051.x
• S. Hochreiter and J. Schmidhuber. Long short-term memory. Neur. Comput. 9.8 (1997), pp. 1735–1780. doi: 10.1162/neco.1997.9.8.1735
• P. R. Israilevich, G. J. D. Hewings, M. Sonis, and G. R. Schindler. Forecasting structural change with a regional econometric input-output model. J. Region. Sci. 37.4 (1997), pp. 565–590. doi: 10.1111/0022-4146.00070
• W. Lu, J. Li, Y. Li, A. Sun, and J. Wang. A CNN-LSTM-based model to forecast stock prices. Neur. Comput. 1, 6622927 (2020), pp. 1–10. doi: 10.1155/2020/6622927
• S. Makridakis, E. Spiliotis, and V. Assimakopoulos. Statistical and machine learning forecasting methods: Concerns and ways forward. PLoS One 32.3, e0194889 (2018). doi: 10.1371/journal.pone.0194889
• M. C. Medeiros, G. F. Vasconcelos, Á. Veiga, and E. Zilberman. Forecasting inflation in a data-rich environment: The benefits of machine learning methods. J. Bus. Econ. Stat. 39.1 (2021), pp. 98–119. doi: 10.1080/07350015.2019.1637745
• I. Moosa and K. Burns. The random walk as a forecasting benchmark: Drift or no drift? Appl. Econ. 48.43 (2016), pp. 4131–4142. doi: 10.1080/00036846.2016.1153788
• N. Nonejad. Point forecasts of the price of crude oil: An attempt to ‘beat’ the end-of-month random-walk benchmark. Empir. Econ. 67 (2024), pp. 1497–1539. doi: 10.1007/s00181-024-02599-8
• A. Panagiotelis, G. Athanasopoulos, R. J. Hyndman, B. Jiang, and F. Vahid. Macroeconomic forecasting for Australia using a large number of predictors. Int. J. Forecast. 35.2 (2019), pp. 616–633. doi: 10.1016/j.ijforecast.2018.12.002
• O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu. Financial time series forecasting with deep learning: A systematic literature review: 2005–2019. Appl. Soft Comput. 90, 106181 (2020). doi: 10.1016/j.asoc.2020.106181
• Australian Bureau of Statistics. Australian economic indicators. accessed 20th November 2024. 2024. url: https://www.abs.gov.au/statistics
• Z. I. Taskin, K. Yildirak, and C. H. Aladag. An enhanced random forest approach using CoClust clustering: MIMIC-III and SMS spam collection application. J. Big Data 10.1, 38 (2023). doi: 10.1186/s40537-023-00720-9
• J. F. Torres, D. Hadjout, A. Sebaa, F. Martínez-Álvarez, and A. Troncoso. Deep learning for time series forecasting: A survey. Big Data 9.1 (2020), pp. 3–21. doi: 10.1089/big.2020.0159 on p. C169).
• G. R. West. Comparison of input-output, input-output + econometric and computable general equilibrium impact models at the regional level. Econ. Sys. Res. 7.2 (1995), pp. 209–227. doi: 10.1080/09535319500000021
• J. Yoon. Forecasting of real GDP growth using machine learning models: Gradient boosting and random forest approach. Comput. Econ. 57.1 (2021), pp. 247–265. doi: 10.1007/s10614-020-10054-w
• Y. Zheng, Z. Xu, and A. Xiao. Deep Learning in economics: A systematic and critical review. A. I. Rev. 56.9 (2023), pp. 9497–9539. doi: 10.1007/s10462-022-10272-8