2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics
| Format: | General Document |
|---|
| _version_ | 1860798323120668672 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2024-09-07 |
| format | General Document |
| id | 17189 |
| institution | UniSZA |
| originalfilename | 17189_30692d5007ab823.pdf |
| person | Md Abdullah |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=17189 |
| sourcemedia | Server storage Scanned document |
| spelling | 17189 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=17189 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Business and Management English application/pdf 1.7 309 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access Universiti Sultan Zainal Abidin Copyright©PWB2025 Deep learning Tourism—Economic aspects Dissertations, Academic Deep learning (Machine learning) Md Abdullah Halal tourism Shariah-compliant tourism Tourism stock performance Big data analytics Portfolio diversification Reinforcement learning Sustainable tourism industry Islamic tourism industry Sustainable tourism—Management Big data—Economic aspects Portfolio management 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics The development of halal tourism destinations among Muslim and non-Muslim majority countries faces challenges in terms of diverse meanings of the term halal, level of income and awareness, location, as well as the lack of unified global standards of certification, financial constraints, and gender differences. Policymakers and regulators face difficulties in formulating policies for conclusive growth and infrastructure development. Moreover, investors and decision-makers are also hesitant to invest in this new industry due to the difficulty in measuring its performance. There are four main research objectives in this study. First, to investigate the impact of halal tourism industry performance on Shariah-compliant tourism stock return. Second, to forecast Shariah-compliant tourism stock prices using deep learning and textual analysis. Third, to examine the portfolio diversification benefits of Shariah-compliant tourism stocks. Lastly, to develop a tail risk portfolio optimization model using deep reinforcement learning techniques. This study formulated hypotheses by integrating the coalignment theory, stakeholder theory, current portfolio theory, and the noisy trader hypothesis. It covers the sample period of 2008 to 2021, and the data was collected from Twitter, Google Trend, Datastream, World Bank, and other publicly available sources. This study considers 192 Shariah-compliant listed hospitality and tourism firms from 38 countries as halal tourism firms. For empirical analysis, this study employed applied econometrics and deep learning techniques to achieve different objectives. The generalized method of moments and panel quantile regression are used for objective one, sentiment analysis and deep learning for objective two, time-varying parameter vector autoregressions based connectedness approach for objective three, and deep reinforcement learning for objective four. The results of objective one indicate that industry sustainability practices have a positive influence on Shariah-compliant tourism stock return, supported by the stakeholder theory. Moving on to objective two, the findings demonstrate that industry sentiment can effectively contribute to stock price forecasting, which is supported by the noise trader hypothesis. In objective three, the study reveals that Shariah-compliant tourism stocks can be diversified within traditional assets. Lastly, the results of objective four indicate that the tail risk portfolio model, coupled with industry sentiment and deep reinforcement learning, outperformed both baseline and min-variance portfolios. The findings of this study contribute significantly by empowering policymakers and destination managers in shaping sustainable halal tourism policies and enhancing destination reputations. Additionally, the study's findings on deep reinforcement learning portfolios, industry-specific sentiment indices, and the impact of sustainable performance on stock returns offer valuable insights for investors and portfolio managers. It assists them in optimizing performance and navigating market uncertainties effectively. These contributions have far-reaching implications for both the tourism and financial sectors, influencing strategic decision-making and risk management practices. 2024-09-07 uuid:4162BA63-9974-483E-8562-CF2E93D181E2 17189_30692d5007ab823.pdf Adobe PDF Services Thesis |
| spellingShingle | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| state | Terengganu |
| subject | Tourism—Economic aspects Dissertations, Academic Deep learning (Machine learning) Islamic tourism industry Sustainable tourism—Management Big data—Economic aspects Portfolio management |
| summary | The development of halal tourism destinations among Muslim and non-Muslim majority countries faces challenges in terms of diverse meanings of the term halal, level of income and awareness, location, as well as the lack of unified global standards of certification, financial constraints, and gender differences. Policymakers and regulators face difficulties in formulating policies for conclusive growth and infrastructure development. Moreover, investors and decision-makers are also hesitant to invest in this new industry due to the difficulty in measuring its performance. There are four main research objectives in this study. First, to investigate the impact of halal tourism industry performance on Shariah-compliant tourism stock return. Second, to forecast Shariah-compliant tourism stock prices using deep learning and textual analysis. Third, to examine the portfolio diversification benefits of Shariah-compliant tourism stocks. Lastly, to develop a tail risk portfolio optimization model using deep reinforcement learning techniques. This study formulated hypotheses by integrating the coalignment theory, stakeholder theory, current portfolio theory, and the noisy trader hypothesis. It covers the sample period of 2008 to 2021, and the data was collected from Twitter, Google Trend, Datastream, World Bank, and other publicly available sources. This study considers 192 Shariah-compliant listed hospitality and tourism firms from 38 countries as halal tourism firms. For empirical analysis, this study employed applied econometrics and deep learning techniques to achieve different objectives. The generalized method of moments and panel quantile regression are used for objective one, sentiment analysis and deep learning for objective two, time-varying parameter vector autoregressions based connectedness approach for objective three, and deep reinforcement learning for objective four. The results of objective one indicate that industry sustainability practices have a positive influence on Shariah-compliant tourism stock return, supported by the stakeholder theory. Moving on to objective two, the findings demonstrate that industry sentiment can effectively contribute to stock price forecasting, which is supported by the noise trader hypothesis. In objective three, the study reveals that Shariah-compliant tourism stocks can be diversified within traditional assets. Lastly, the results of objective four indicate that the tail risk portfolio model, coupled with industry sentiment and deep reinforcement learning, outperformed both baseline and min-variance portfolios. The findings of this study contribute significantly by empowering policymakers and destination managers in shaping sustainable halal tourism policies and enhancing destination reputations. Additionally, the study's findings on deep reinforcement learning portfolios, industry-specific sentiment indices, and the impact of sustainable performance on stock returns offer valuable insights for investors and portfolio managers. It assists them in optimizing performance and navigating market uncertainties effectively. These contributions have far-reaching implications for both the tourism and financial sectors, influencing strategic decision-making and risk management practices. |
| title | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| title_full | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| title_fullStr | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| title_full_unstemmed | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| title_short | 2024_Sustainability, Forecasting, And Portfolio Diversification Benefits Of Global Halal Tourism Industry Using Big Data Analytics |
| title_sort | 2024_sustainability, forecasting, and portfolio diversification benefits of global halal tourism industry using big data analytics |