Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?

This paper investigates if machine learning (ML) models are able to produce accurate real-time nowcasts of Singapore’s GDP. Adopting dynamic factors with the Kalman smoother approach to simulate a realistic nowcasting exercise that incorporates the publication lags of variables, we evaluate the...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheong, Wei Si, Tan, Hong Bing, Wise, Vincent
Other Authors: WANG, Wei-Siang
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2021
Subjects:
Online Access:https://hdl.handle.net/10356/147309
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-147309
record_format dspace
spelling sg-ntu-dr.10356-1473092023-03-05T15:46:25Z Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP? Cheong, Wei Si Tan, Hong Bing Wise, Vincent WANG, Wei-Siang School of Social Sciences WSWANG@ntu.edu.sg Social sciences::Economic theory This paper investigates if machine learning (ML) models are able to produce accurate real-time nowcasts of Singapore’s GDP. Adopting dynamic factors with the Kalman smoother approach to simulate a realistic nowcasting exercise that incorporates the publication lags of variables, we evaluate the nowcasting accuracy of a suite of ML models, which includes the Elastic Net, Random Forest (RF), Gradient Boosted Trees (GBT), and Support Vector Regression (SVR), alongside simple ensembles. The models are assessed against the autoregressive model (AR) and the dynamic factor model (DFM) which act as benchmarks. In addition, we investigate if the ML models’ variable importance metrics are able to point policymakers towards the underlying economic indicators that would be useful to monitor, to address the common critique of ML models in lacking interpretability. We find that all four ML models were superior to the AR benchmark, but only the linear ML models (SVR & Elastic Net) outperformed the DFM benchmark and were robust in both calm and volatile periods. On the other hand, the tree-based models (RF & GBT) performed well only in calmer periods, which revealed their limitations in extrapolation. The simple ensemble models were also competitive and provided accuracy gains over most ML models individually. We also find that the ML models were able to appropriately assign high importance to variables in a way that conforms with Singapore’s economic structure and the business cycle literature. In sum, we find that the use of ML models helps to improve nowcasts of Singapore’s GDP. Bachelor of Arts in Economics 2021-03-31T07:19:17Z 2021-03-31T07:19:17Z 2021 Final Year Project (FYP) Cheong, W. S., Tan, H. B. & Wise, V. (2021). Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/147309 https://hdl.handle.net/10356/147309 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Social sciences::Economic theory
spellingShingle Social sciences::Economic theory
Cheong, Wei Si
Tan, Hong Bing
Wise, Vincent
Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
description This paper investigates if machine learning (ML) models are able to produce accurate real-time nowcasts of Singapore’s GDP. Adopting dynamic factors with the Kalman smoother approach to simulate a realistic nowcasting exercise that incorporates the publication lags of variables, we evaluate the nowcasting accuracy of a suite of ML models, which includes the Elastic Net, Random Forest (RF), Gradient Boosted Trees (GBT), and Support Vector Regression (SVR), alongside simple ensembles. The models are assessed against the autoregressive model (AR) and the dynamic factor model (DFM) which act as benchmarks. In addition, we investigate if the ML models’ variable importance metrics are able to point policymakers towards the underlying economic indicators that would be useful to monitor, to address the common critique of ML models in lacking interpretability. We find that all four ML models were superior to the AR benchmark, but only the linear ML models (SVR & Elastic Net) outperformed the DFM benchmark and were robust in both calm and volatile periods. On the other hand, the tree-based models (RF & GBT) performed well only in calmer periods, which revealed their limitations in extrapolation. The simple ensemble models were also competitive and provided accuracy gains over most ML models individually. We also find that the ML models were able to appropriately assign high importance to variables in a way that conforms with Singapore’s economic structure and the business cycle literature. In sum, we find that the use of ML models helps to improve nowcasts of Singapore’s GDP.
author2 WANG, Wei-Siang
author_facet WANG, Wei-Siang
Cheong, Wei Si
Tan, Hong Bing
Wise, Vincent
format Final Year Project
author Cheong, Wei Si
Tan, Hong Bing
Wise, Vincent
author_sort Cheong, Wei Si
title Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
title_short Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
title_full Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
title_fullStr Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
title_full_unstemmed Can machine learning algorithms lead to more accurate nowcasts of Singapore's GDP?
title_sort can machine learning algorithms lead to more accurate nowcasts of singapore's gdp?
publisher Nanyang Technological University
publishDate 2021
url https://hdl.handle.net/10356/147309
_version_ 1759857108079083520