Background: This paper proposes a method for reducing model errors in regressions when modelling macroeconomic variables by using machine learning algorithms and traditional time series regression models.
Methods: In this paper, machine learning models are subjected to repeated k-fold cross validation and hyperparameter tuning. The traditional time series model is subjected to weighted polynomial functional forms. The total sample of macroeconomic data has 440 monthly observations and 146 quarterly observations.
Results: The kernel support vector machine show superior results than any other machine learning model that the study adopted. Furthermore, the kernel support vector machine model outperforms the traditional time series model Mixed Data Sampling Auto Regressive Distribution Lag model which is run without repeated k-fold cross validation and hyperparameter tuning.
Recommendations: The results show that integrating repeated k-fold cross validation with hyperparameter tuning increases the overall performance of machine learning algorithms and each model records the average outcome from all folds and runs. The optimal model is chosen with the lowest root mean square error, lowest mean absolute error and the highest goodness of fit (R-Squared). These findings demonstrate how machine learning models outperform the traditional time series model.

CHAPTER 1 9
INTRODUCTION 9
1.1 Background 9
1.2 Problem statement 9
1.3 Objective of this study 10
1.4 Thesis Research Structure 11
CHAPTER 2 13
LITERATURE REVIEW 13
CHAPTER 3 19
DATA AND METHODOLOGY 19
3.1 Variables of Interest. 20
3.2 Data Split 21
3.3 Hyperparameter optimisation of machine learning algorithms 21
3.3.1 SVM Parameter Tuning 21
3.3.2 Parameter Tuning for boosting trees 22
3.3.3 eXtreme gradient boosting -Parameter Tuning 23
3.3.4 Random forest - Parameter Tuning 23
3.4 Framework for Benchmark Model. 24
3.4.1 Midasml 24
3.4.2 The MIDAS ARDL Model 25
3.5 Variable importance 25
CHAPTER 4 27
EMPIRICAL RESULTS 27
4.1 Overall Predictive Performance 27
4.2 Our findings 28
4.3 Overall Economic Volatility Prediction 29
4.4 Model Assessment for Volatility Prediction 30
4.5 Variables Assessment 39
CHAPTER 5 41
DISCUSSION 41
CHAPTER 6 43
CONCLUSION 43
References 45
A.1 Data 49
A.2 Supplementary Results 51
A.3 MIDAS ARDL Results 52

Ataei, M., Lohmann, B., Khaki-Sedigh, A., & Lucas, C. (2004). Model based method for estimating an attractor dimension from uni/multivariate chaotic time series with application to Bremen climatic dynamics. Chaos, Solitons & Fractals, 19(5), 1131-1139.
Athey, S. (2019). 21. The Impact of Machine Learning on Economics. In The economics of artificial intelligence (pp. 507-552). University of Chicago Press.
Ay, M., Stenger, D., Schwenzer, M., Abel, D., & Bergs, T. (2019). Kernel Selection for Support Vector Machines for System Identification of a CNC Machining Center. IFAC-PapersOnLine, 52(29), 192-198.
Babii, A., Ghysels, E., & Striaukas, J. (2021). Machine learning time series regressions with an application to nowcasting. Journal of Business & Economic Statistics, 1-23.
Bai, J., & Ng, S. (2008). Large dimensional factor analysis. Now Publishers Inc.
Barra, M. (2010). Is there a link between GDP growth and equity returns? Research Bulletin.
Beer, S., De Mooij, R., & Liu, L. (2020). International corporate tax avoidance: A review of the channels, magnitudes, and blind spots. Journal of Economic Surveys, 34(3), 660-688.
Bernanke, B. S., Gertler, M., Watson, M., Sims, C. A., & Friedman, B. M. (1997). Systematic monetary policy and the effects of oil price shocks. Brookings papers on economic activity, 1997(1), 91-157.
Bikkina, V. (2014). Comparison of machine learning methods for predicting bird distributions https://ir.library.oregonstate.edu/downloads/gt54kp874
Boivin, J., & Ng, S. (2006). Are more data always better for factor analysis? Journal of Econometrics, 132(1), 169-194. https://doi.org/10.1016/j.jeconom.2005.01.027
Bolhuis, M., & Rayner, B. (2020). Deus ex Machina? A Framework for Macro Forecasting with Machine Learning. International Monetary Fund. Working Paper No. 20/45.
Breiman, L. (2001). Random forests. Machine learning, 45(1), 5-32.
Chakraborty, C., & Joseph, A. (2017). Machine learning at central banks. Bank of England. Working Paper No. 674.
Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining,
Clements, M. P., & Galvão, A. B. (2008). Macroeconomic forecasting with mixed-frequency data: Forecasting output growth in the United States. Journal of Business & Economic Statistics, 26(4), 546-554.
Cobham, A., & Janský, P. (2018). Global distribution of revenue loss from corporate tax avoidance: re‐estimation and country results. Journal of International Development, 30(2), 206-232.
Foroni, C., Marcellino, M., & Schumacher, C. (2015). Unrestricted mixed data sampling (MIDAS): MIDAS regressions with unrestricted lag polynomials. Journal of the Royal Statistical Society. Series A (Statistics in Society), 57-82.
Ghysels, E., Sinko, A., & Valkanov, R. (2007). MIDAS regressions: Further results and new directions. Econometric reviews, 26(1), 53-90.
Giannone, D., Miranda, A. S., & Michele, M. (2013). Nowcasting China Real GDP https://www.cirano.qc.ca/conferences/public/pdf/realtime2013/Papers/Giannone_Miranda.pdf
Giannone, D., Reichlin, L., & Small, D. (2008). Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4), 665-676.
Goodwin, N., Harris, J. M., Nelson, J. A., Roach, B., & Torras, M. (2015). Principles of Economics in Context. 2nd Ed. Routledge.
Hebous, M. S., Klemm, M. A. D., & Wu, Y. (2021). How Does Profit Shifting Affect the Balance of Payments? International Monetary Fund Working Paper No. 2021/041.
Hothorn, T., Hornik, K., & Zeileis, A. (2006). Unbiased recursive partitioning: A conditional inference framework. Journal of Computational and Graphical statistics, 15(3), 651-674.
Hsu, C.-W., Chang, C.-C., & Lin, C.-J. (2003). A practical guide to support vector classification. In: Taipei.
Jung, J.-K., Patnam, M., & Ter-Martirosyan, A. (2018). An algorithmic crystal ball: forecasts-based on machine learning. International Monetary Fund Working Paper No. 18/230.
Karatzoglou, A., Smola, A., Hornik, K., & Zeileis, A. (2004). kernlab-an S4 package for kernel methods in R. Journal of statistical software, 11(9), 1-20.
Krkoska, L., & Teksoz, U. (2007). Accuracy of GDP growth forecasts for transition countries: Ten years of forecasting assessed. International Journal of Forecasting, 23(1), 29-45.
Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., Mayer, Z., Kenkel, B., & Team, R. C. (2020). Package ‘caret’. The R Journal, 20(1),223.
Kuzin, V., Marcellino, M., & Schumacher, C. (2011). MIDAS vs. mixed-frequency VAR: Nowcasting GDP in the euro area. International Journal of Forecasting, 27(2), 529-542.
Liu, H., & Hall, S. G. (2001). Creating high‐frequency national accounts with state‐space modelling: a Monte Carlo experiment. Journal of Forecasting, 20(6), 441-449.
Long, G. (2010). GDP prediction by support vector machine trained with genetic algorithm. 2010 2nd International Conference on Signal Processing Systems,
Lüdecke, D., Ben-Shachar, M. S., Patil, I., & Makowski, D. (2020). Extracting, computing and exploring the parameters of statistical models using R. Journal of Open Source Software, 5(53), 2445.
Marcellino, M., Stock, J. H., & Watson, M. W. (2003). Macroeconomic forecasting in the euro area: Country specific versus area-wide information. European Economic Review, 47(1), 1-18.
Mariano, R. S., & Murasawa, Y. (2003). A new coincident index of business cycles based on monthly and quarterly series. Journal of applied Econometrics, 18(4), 427-443.
Mariano, R. S., & Murasawa, Y. (2010). A coincident index, common factors, and monthly real GDP. Oxford Bulletin of Economics and Statistics, 72(1), 27-46.
Morvan, M. L., Josse, J., Scornet, E., & Varoquaux, G. (2021). What's a good imputation to predict with missing values? arXiv preprint arXiv:2106.00311.
Premraj, P. (2019). Forecasting GDP growth: a comprehensive comparison of employing machine learning algorithms and time series regression models (Masters Thesis)
Probst, P., & Boulesteix, A.-L. (2017). To Tune or Not to Tune the Number of Trees in Random forest. J. Mach. Learn. Res., 18(1), 6673-6690.
Qureshi, S., Chu, B. M., & Demers, F. S. (2020). Forecasting Canadian GDP growth using XGBoost (Masters Thesis).
Richardson, A., & Mulder, T. (2018). Nowcasting New Zealand GDP using machine learning algorithms. International Workshop and Seminar on “Big Data for Central Bank Policies / Building Pathways for Policy Making with Big Data”, Indonesia.
Robertson, J. C., & Tallman, E. W. (1999). Vector autoregressions: forecasting and reality. Economic Review-Federal Reserve Bank of Atlanta, 84(1), 4.
Shao, X. (2010). The dependent wild bootstrap. Journal of the American Statistical Association, 105(489), 218-235.
Simon, N., Friedman, J., Hastie, T., & Tibshirani, R. (2013). A sparse-group lasso. Journal of computational and graphical statistics, 22(2), 231-245.
Stock, J. H. (1991). Confidence intervals for the largest autoregressive root in US macroeconomic time series. Journal of monetary economics, 28(3), 435-459.
Stock, J. H., & Watson, M. W. (1989). New indexes of coincident and leading economic indicators. NBER macroeconomics annual, 4, 351-394.
Strobl, C., Boulesteix, A.-L., Zeileis, A., & Hothorn, T. (2007). Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC bioinformatics, 8(1), 1-21.
Suykens, J. A., Vandewalle, J., & De Moor, B. (2001). Optimal control by least squares support vector machines. Neural networks, 14(1), 23-35.
Tamara, N., Dwi Muchisha, N., Andriansyah, A., & Soleh, A. M. (2020). Nowcasting Indonesia’s GDP Growth Using Machine Learning Algorithms.
Tørsløv, T. R., Wier, L. S., & Zucman, G. (2018). The missing profits of nations. No. w24701. National Bureau of Economic Research.