Nowcasting Madagascar's real GDP using machine learning algorithms

Ramaharo, Franck M. and Rasolofomanana, Gerzhino H. (2023): Nowcasting Madagascar's real GDP using machine learning algorithms.

Abstract

We investigate the predictive power of different machine learning algorithms to nowcast Madagascar's gross domestic product (GDP). We trained popular regression models, including linear regularized regression (Ridge, Lasso, Elastic-net), dimensionality reduction model (principal component regression), k-nearest neighbors algorithm (k-NN regression), support vector regression (linear SVR), and tree-based ensemble models (Random forest and XGBoost regressions), on 10 Malagasy quarterly macroeconomic leading indicators over the period 2007Q1-2022Q4, and we used simple econometric models as a benchmark. We measured the nowcast accuracy of each model by calculating the root mean square error (RMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Our findings reveal that the Ensemble Model, formed by aggregating individual predictions, consistently outperforms traditional econometric models. We conclude that machine learning models can deliver more accurate and timely nowcasts of Malagasy economic performance and provide policymakers with additional guidance for data-driven decision making.

• Item Type: MPRA Paper
• Language: English
• Keywords: nowcasting; gross domestic product; machine learning; Madagascar
• Subjects: C - Mathematical and Quantitative Methods > C0 - General > C02 - Mathematical Methods; C - Mathematical and Quantitative Methods > C5 - Econometric Modeling > C53 - Forecasting and Prediction Methods ; Simulation Methods; C - Mathematical and Quantitative Methods > C6 - Mathematical Methods ; Programming Models ; Mathematical and Simulation Modeling > C63 - Computational Techniques ; Simulation Modeling; E - Macroeconomics and Monetary Economics > E1 - General Aggregative Models > E17 - Forecasting and Simulation: Models and Applications

References

Mohamed F. Abd El-Aal, Diaa Salama AbeElminaamb & Alaa-Eldin Abd-Elatif (2023), 'Nowcasting Egypt GDP using machine learning algorithms'', Journal of Computing and Communication, 2(1), 1-8.

Sunday C. Agu, Fergus U. Onu, Uchenna K. Ezemagu & D. Oden (2022), ''Predicting gross domestic product to macroeconomic indicators'', Intelligent Systems with Applications, 14, 1-7.

Josué R. Andrianady, Njakanasandratra R. Rajaonarison & Gerzhino H. Rasolofomanana (2023), ''Analyse des impacts de la tension Russie-Ukraine à Madagascar'', Munich Personal RePEc Archive, 116561, University Library of Munich.

Karim Barhoumi, Seung Mo Choi, Tara Iyer, Jiakun Li, Franck Ouattara, Andrew Tiffin & Jiaxiong Yao (2022), ''Overcoming data sparsity: A Machine Learning approach to track the real-time impact of COVID-19 in Sub-Saharan Africa'', IMF Working Paper, 2022/088, International Monetary Fund.

Juan Barrios, Julia Escobar, Janelle Leslie, Lucía Martín, Werner Peña (2021), ''Nowcasting to predict economic activity in real time: the cases of Belize and El Salvador'', IDB Monograph, IDB-MG-970, Inter-American Development Bank.

John~M. Bates, & Clive W. Granger (1969), ''The combination of forecasts'', Journal of the Operational Research Society, 20(4), 451-468.

Kristian N. Bentsen & Denis Gorea (2021), 'Nowcasting and forecasting economic activity in Denmark using payment system data'', Danmarks Nationalbank Working, 177, Danmarks Nationalbank.

Christoph Bergmeir & José M. Benítez (2012), ''On the use of cross-validation for time series predictor evaluation'', Information Sciences, 191, 192-213.

Banky Foiben'i Madagasikara (BFM), ''Bulletin de la BFM''. Retrieved July 01, 2023, from https://www.banky-foibe.mg/vente_bulletin-de-bfm

Banky Foiben'i Madagasikara (2019), Rapport Annuel 2019, Direction de la Documentation et des Centrales d'information, Banky Foiben'i Madagasikara.

Banky Foiben'i Madagasikara (2020), Rapport Annuel 2020, Direction de la Documentation et des Centrales d'information, Banky Foiben'i Madagasikara.

Banky Foiben'i Madagasikara (2021), Rapport Annuel 2021, Direction de la Documentation et des Centrales d'information, Banky Foiben'i Madagasikara.

Banky Foiben'i Madagasikara (2022), Rapport Annuel 2022, Direction de la Documentation et des Centrales d'information, Banky Foiben'i Madagasikara.

Banky Foiben'i Madagasikara (BFM), ''Rapport Annuel''. Retrieved July 01, 2023, from https://www.banky-foibe.mg/_rapport-annuel

Rudrani Bhattacharya, Bornali Bhandari & Sudipto Mundle (2023), ''Nowcasting India’s quarterly GDP growth: A factor Augmented Time-Varying Coefficient Regression Model (FA-TVCRM)'', Journal of Quantitative Economics, 21, 213-234.

Alan S. Blinder (2008), ''Keynesian economics'', Concise Encyclopedia of Economics. Retrieved July 01, 2023, from http://www.econlib.org/library/Enc/KeynesianEconomics.html

Byron Botha, Tim Olds, Geordie Reid, Daan Steenkamp & Rossouw van Jaarsveld (2021), ''Nowcasting South African gross domestic product using a suite of statistical models'', SARB Working Paper, WP/21/01, South African Reserve Bank.

Leo Breiman (2001), ''Random Forests'', Machine Learning, 45, 5-32.

Tianqi Chen & Carlos Guestrin (2016), ''XGBoost: A scalable tree boosting system'', arXiv preprint, arXiv:1603.02754.

Ba Chu & Shafiullah Qureshi (2023), ''Comparing out-of-sample performance of Machine Learning methods to forecast U.S. GDP growth'', Computational Economics, 62, 1567-1609.

Giovanni Cicceri, Inserra Giuseppe & Michele Limosani (2020), ''A machine learning approach to forecast Economic recessions - An Italian case study'', Mathematics, 8(2), 1-20.

Courtney Cochrane, ''Time Series Nested Cross-Validation'', Retrieved August 10, 2023, from https://towardsdatascience.com/time-series-nested-cross-validation-76adba623eb9

Jean-François Dauphin, Kamil Dybczak, Morgan Maneely, Marzie T. Sanjani, Nujin Suphaphiphat, Yifei Wang & Hanqi Zhang (2022), ''\Nowcasting GDP: A scalable approach using DFM, machine learning and novel data, applied to European economies'', IMF Working Paper, WP/22/52, International Monetary Fund.

Douane Malagasy, ''Les statistiques - Commerce exterieur''. Retrieved August 01, 2023, from http://www.douanes.gov.mg/statistiques-et-bilan/

Martin D. D. Evans (2005), ''Where are we now? Real-time tstimates of the macroeconomy'', International Journal of Central Banking, 1(2), 127-175.

Paolo Fornaro & Henri Luomaranta (2020), ''Nowcasting Finnish real economic activity: a machine learning approach'', Empirical Economics, 58, 55-71.

Jerome H. Friedman (2001), ''Greedy function approximation: A gradient boosting machine'', The Annals of Statistics, 29(5), 1189-1232.

Saurabh Ghosh & Abhishek Ranjan, ''A machine learning approach to GDP nowcasting: An emerging market experience'', Bulletin of Monetary Economics and Banking, Bank Indonesia, 26(0), 33-54.

Domenico Giannone, Lucrezia Reichlin & David Small (2008), ''Nowcasting: The real-time informational content of macroeconomic data'', Journal of Monetary Economics, 55(4), 665-676,

Selçuk Gül & Abdullah Kazdal (2021), ''Nowcasting and short-term forecasting Turkish GDP: Factor-MIDAS approach'', TCMB Working Paper, 21/11, Central Bank of the Republic of Turkey.

Daniel Hopp (2022), ''Benchmarking econometric and machine learning methodologies in nowcasting'', UNCTAD Research Paper, 83, United Nations Conference on Trade and Development.

Amman Hossain, Md Hossen, Md M. Hasan & Abdus Sattar (2021), ''GDP growth prediction of Bangladesh using machine learning algorithm'', Proceeding of the 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India, pp. 812-817.

Institut National de la Statistique (INSTAT), ''Impacts du coronavirus sur l'économie Malagasy'', Wayback Machine (November 16, 2022) Retrieved August 02, 2023, from https://web.archive.org/web/20221116133351/https://www.instat.mg/p/impacts-du-coronavirus-sur-leconomie-malagasy

Institut National de la Statistique (INSTAT), ''Comptes Nationaux'', Wayback Machine (June 02, 2023) Retrieved August 02, 2023, from https://web.archive.org/web/20230602143320/https://www.instat.mg/thematique/comptes-nationaux

Institut National de la Statistique (INSTAT), ''Indice des prix à la Consommation (IPC)'', Wayback Machine (January 20, 2022). Retrieved August 10, 2023, from https://web.archive.org/web/20220120074937/https://www.instat.mg/statistiques/bases-de-donnees/nipc

Institut National de la Statistique (INSTAT), ''Tableau de Bord de l'Économie'', Wayback Machine (September 28, 2022) Retrieved August 10, 2023, from https://web.archive.org/web/20220928222805/http://www.instat.mg/thematique/economie

Kentaro Ito & Ryohei Nakano (2003), ''Optimizing support vector regression hyperparameters based on cross-validation'', Proceedings of the International Joint Conference on Neural Networks, 3, pp. 2077-2082.

Siti K. Jasni, Fatin E. M. Aris & Veronica S. Jamila (2022), ''Nowcasting Malaysia’s GDP using Machine Learning'', in Proceedings of the 9th Malaysia Statistics Conference 2022, Institut Latihan Statistik Malaysia.

Jiro sy Rano Malagasy (JIRAMA), ''Consommation d'électricité par branches d'activités (2007-2022)'' [unpublished raw data], JIRAMA, Madagascar.

Kristian Jönsson (2020), ''Machine learning and nowcasts of Swedish GDP'', Journal of Business Cycle Research, 16, 123-134.

Jin-Kyu Jung, Manasa Patnam & Anna Ter-Martirosyan (2018), ''An algorithmic crystal ball: Forecasts-based on machine learning'', IMF Working Paper, WP/18/230, International Monetary Fund.

Dennis Kant, Andreas Pick & Jasper de Winter (2022), ''Nowcasting GDP using machine learning methods'', DNB Working papers, 754, De Nederlandsche Bank NV.

Rusul S. Kadhim & Dhahir A. Reda (2023), ''Employing boosting algorithms to predict the growth of the Iraqi GDP'', Journal of Higher Education Theory and Practice, 23(01), 59-73.

Davor Kunovac & Borna Špalat (2014), ''Nowcasting GDP using available monthly indicators'', HNB Working Paper, W-39, Croatian National Bank.

Benedikt Maas (2019), ''Nowcasting and forecasting US recessions: Evidence from the Super Learner'', Munich Personal RePEc Archive Paper, 96408, University Library of Munich.

Mikheil Mgebrishvili (2022), ''Nowcasting with high frequency data, Google trends and machine learning'', MOF Working Paper, WP 01/2022, Ministry of Finance of Georgia.

Ministère de l'Économie et des Finances, ''Transparence budgétaire et financière liée á la période COVID-19''. Retrieved December 03, 2022, from http://www.mef.gov.mg/reportingcovid

Ministère du Tourisme (MINTOUR), ''Données Statistiques sur le Tourisme (2007-2022)'' [unpublished raw data], MINTOUR, Madagascar.

Rickard Nyman & Paul Ormerod (2017), ''Predicting economic recessions using machine learning algorithms'', arXiv preprint, arXiv:1701.01428.

Office Malgache des Hydrocarbures (OMH), ''Bulletin Pétrolier (Le Marché Pétrolier au 1er, 2ème, 3ème, 4ème trimestre 2021)''. Retrieved August 10, 2023, from http://www.omh.mg/index.php?idm=5&CL=bulpetro

Office Malgache des Hydrocarbures (OMH), ''Ventes nationales de produits pétroliers (2007-2022)'' [Unpublished raw data], OMH, Madagascar.

Tommaso Proietti, Alessandro Giovannelli, Ottavio Ricchi, Ambra Citton, Christían Tegami & Cristina Tinti (2021), Nowcasting GDP and its components in a data-rich environment: The merits of the indirect approach'', International Journal of Forecasting, 37(4), 1376-1398.

Anupam Prakash, Chaitali Bhowmick & Ishu Thakur (2023), Real-time monitoring of the Indian economy - An alternative approach, Department of Economic and Policy Research, Reserve Bank of India.

Shafiullah Qureshi, Ba M. Chu & Fanny S. Demers (2020), ''Forecasting Canadian GDP growth using XGBoost'', Carleton Economics Working Paper, CEWP 20-14, Carleton University.

Adam Richardson, Thomas van Florenstein Mulder & Tugrul Vehbi (2018), ''Nowcasting New Zealand GDP using machine learning algorithms'', CAMA Working Paper, 47/2018, Centre for Applied Macroeconomic Analysis, Australian National University.

Adam Richardson, Thomas van Florenstein Mulder & Tugrul Vehbi (2019), ''Nowcasting GDP using machine learning algorithms: A real-time assessment'', RBNZ Discussion Paper, 2019-03, Reserve Bank of New Zealand.

José L. Rossi Júnior & Lucas G. M. de Oliveira (2023), ''Which one predicts better?: Comparing different GDP nowcasting methods using Brazilian data'', IDB Discussion Paper, IDB-DP-01012, Inter-American Development Bank.

Jeremy Smith & Kenneth F. Wallis (2009), ''A simple explanation of the forecast combination puzzle'', Oxford Bulletin of Economics and Statistics, 71, 331-355.

Alex J. Smola & Bernhard Schölkopf (2004), ''A tutorial on support vector regression'', Statistics and Computing, 14, 199-222.

Teo Susnjak & Christoph Schumacher (2018), ''Nowcasting: Towards real-time GDP prediction'', GDP Live Technical Report, 1, Knowledge Exchange Hub, Massey University.

Leonard J. Tashman (2000), ''Out-of-sample tests of forecasting accuracy: an analysis and review'', International Journal of Forecasting, 16(4), 437-450.

Novian Tamara, Nadya D. Muchisha, Andriansyah & Agus M. Soleh (2021), ''Nowcasting Indonesia’s GDP growth using machine learning algorithms'', Munich Personal RePEc Archive Paper, 105235, University Library of Munich.

Juan Tenorio & Wilder Pérez (2023), ''GDP nowcasting with machine learning and unstructured data to Peru'', PEA Working Paper, 197, Peruvian Economic Association.

Andrew Tiffin (2016), ''Seeing in the dark: A machine-learning approach to nowcasting in Lebanon'', IMF Working Paper, WP/16/56, International Monetary Fund.

Trésor Public Malagasy, ''Opérations Globales du Trésor (OGT)'', Retrieved August 10, 2023, from http://www.tresorpublic.mg/?page_id=214&content=temp&type=ogt

Blerina Vika & Klea Çupi (2022), ''Forecasting real GDP growth in Albania: Considering ML models as an alternative'', International Conference ''Circular Economy: Opportunities and Challenges'', pp. 246-254.

Yinghan Xia (2023), ''A novel combination machine learning model for regional GDP prediction: evidence from China'', In Proceedings of the 3rd International Conference on Management Science and Software Engineering (ICMSSE 2023), Atlantis Highlights in Engineering, pp. 985-993.

Jaehyun Yoon (2021), ''Forecasting of real GDP growth using Machine Learning models: Gradient Boosting and Random Forest Approach'', Computational Economics, 57, 247-265.

Qin Zhang, He Ni & Hao Xu (2023), ''Nowcasting Chinese GDP in a data-rich environment: Lessons from machine learning algorithms'', Economic Modelling, 122, 1-15.