Halal tourism demand and firm performance forecasting: new evidence from machine learning

ABSTRACT

This study forecasts both Halal tourism demand (HTD) and the financial performance of Halal tourism industry of Malaysia using machine learning. Based on the data over the period from 2009 to 2020, this study considered 338,233 tweets sentiments, and 11 Google trend keywords, firm-specific variables, and macroeconomic variables for HTD and financial performance forecasting. Out of 14 machine learning algorithms, this study found Bagged classification and regression trees method outperforms other forecasting models. The forecasting accuracy scores of HTD and firm financial performance models are 93.71% and 80.12%, respectively. The results reveal that internet data variables (Twitter & Google Trend) significantly contribute to the forecasting models. Evidently, our models functioned optimally during the COVID-19 pandemic. This study offers valuable insights for policymakers to devise sustainable Halal tourism.

KEYWORDS:

• Halal tourism demand forecasting
• Halal tourism profitability
• machine learning
• sentiment analysis
• COVID-19

JEL CLASSIFICATIONS:

• C53
• G3
• Z3

Acknowledgements

The authors would like to thank the editor and the anonymous reviewers for their insightful and constructive comments. This article constitutes part of the preliminary project phase. Earlier version of this article was presented at the Global Tourism Conference 2021, Terengganu, Malaysia on 8 September 2021. The authors also extend their gratitude for the conference reviewers’ constructive feedback.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The authors gratefully acknowledge the Ministry of Higher Education Malaysia for funding the study project through the Fundamental Research Grant Scheme (FRGS/1/2020/SS01/UNISZA/02/1).