Machine learning for predicting tourist spots’ preference and analysing future tourism trends in Bangladesh

Aug 5, 2026

Upload by Aria

This study applies machine learning to Bangladesh’s tourism industry to forecast traveller preferences and future demand trends. Support Vector Machines, Decision Trees, and K-Nearest Neighbors are used for preference prediction, while time-series approaches including ARIMA, Moving Average, and Auto-regression model future trend movements. Results indicate Linear SVM achieves the strongest preference prediction accuracy at 96.3%. For forecasting trends, ARIMA outperforms alternatives, suggesting an unfavourable trajectory. Findings support evidence-based policy and tourism administration decisions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages33

Reading Time1 h 23 min

AccessFree to download

Introduction

Motivation

Methodology

Preference prediction with machine learning

Time-series trend forecasting

Results and discussion

Preference prediction accuracy

Trend forecasting performance

Implications for tourism policy

Enterprise Information Systems ISSN: (Print) (Online) Journal [homepage: ](homepage: www.tandfonline.com/journals/teis20)[www.tandfonline.com/journals/teis20](homepage: www.tandfonline.com/journals/teis20) Machine learning for predicting tourist spots’preference and analysing future tourism trends in Bangladesh Victor Chang, Md Raﬁqul Islam, Abdul Ahad, Md Jobair Ahmed & Qianwen Ariel Xu To cite this article: Victor Chang, Md Raﬁqul Islam, Abdul Ahad, Md Jobair Ahmed & Qianwen Ariel Xu (04 Nov 2024): Machine learning for predicting tourist spots’ preference and analysing future tourism trends in Bangladesh, Enterprise Information Systems, DOI: 10. 1080/17517575 .2024.2415568 To link to this article: [https://doi.org/10.1080/17517575.2024.2415568](https://doi.org/10.1080/17517575.2024.2415568) © 2024 The Author(s) . Published by Informa UK Limited, trading as Taylor & Francis Group. | Published online: 04 Nov 2024. | | --- | | Submit your article to this journal | | View related articles | | View Crossmark data | Full Terms & Conditions of access and use can be found at [https://www.tandfonline.com/action/journalInformation?journalCode=teis20](https://www.tandfonline.com/action/journalInformation?journalCode=teis20) ENTERPRISE INFORMATION SYSTEMS [https://doi.org/10.1080/17517575.2024.2415568](https://doi.org/10.1080/17517575.2024.2415568) Machine learning for predicting tourist spots’ preference and analysing future tourism trends in Bangladesh Victor Changa, Md Rafiqul Islamb, Abdul Ahadc, Md Jobair Ahmedd and Qianwen Ariel Xub a Department of Operations and Information Management, Aston Business School, Aston University, Birmingham, UK; bInformation Systems, Australian Institute of Higher Education (AIH), Australia; cSchool of Computing, Engineering and Digital Technologies, Teesside University, Middlesbrough, UK; dDepartment of Computer Science & Engineering (CSE), City University, Dhaka, Bangladesh ABSTRACT This study uses machine learning, including Support Vector Machines, Decision Trees, K-Nearest Neighbors, to examine Bangladesh’s tourism industry to forecast traveller preferences. We use time series analysis, including ARIMA, Moving Average, and Auto-regression models, to predict future tourism trends. Our results show that, with an accuracy of 96.3%, Linear SVM was the best at predicting preferences. For trend forecasting, the ARIMA model fared better than the others, suggesting that Bangladeshi tourism may be headed in an undesirable direction. Our observations and insights can help guide strategic choices and decisions in the creation of policies and the administration of tourism. ARTICLE HISTORY Received 11 April 2023 Accepted 8 October 2024 KEYWORDS Machine learning; time series analysis; tourism analytics; ARIMA model; support vector machine; bangladesh tourism 1. Introduction Tourism is an important sector in many developing countries, contributing significantly to employment and economic growth. In Bangladesh, tourism has shown good growth potential but remains underdeveloped in terms of technology integration and datadriven decision-making. This study aims to bridge this gap by applying machine learning (ML) techniques to improve the understanding and forecasting accuracy of tourist preferences and future tourism trends. By doing so, this study aims to provide actionable insights to support strategic planning and development of the tourism industry. 1. 1. Motivation Bangladesh is a country in South Asia with an area of 147,570 km2 with a population of 164.5 million population in 2020. It is located in the Indomalaya Ecozone and is very rich and full of natural beauties. Bangladesh owns an ocean coastline, which is 550 kilometres long, and its rivers and lakes account for about 10% of the country’s area. Bangladesh also has many kinds of forests as well as flat land with tall grass (Ahsan CONTACT Victor Chang [v.chang1@aston.ac.uk](v.chang1@aston.ac.uk

FAQs

Which machine learning models are used to predict tourist preferences in Bangladesh?

The study uses Support Vector Machines, Decision Trees, and K-Nearest Neighbors to predict traveller preferences based on the tourism data.

How are future tourism trends forecasted in this research?

Future tourism trends are forecasted using time series analysis methods including ARIMA, Moving Average, and Auto-regression models.

What do the results suggest about Bangladesh’s tourism outlook?

Trend forecasting with ARIMA performs best, and the results suggest Bangladeshi tourism may be moving in an undesirable direction.

Aug 5, 2026

Upload by Aria