Evaluating Forecasting Methods in Tourism: A Systematic Review of Data Sources and Big Data Analytics

Purpose of the study: This study aims to analyze tourism forecasting methods by examining data collection techniques and the types of data used in predictive models. It addresses the need for more accurate forecasting to enhance decision-making in tourism management and policy. Methodology: This research follows a unique bibliometric and systematic literature review (B-SLR) approach, analyzing studies published between 2008 and 2024. The study evaluates various forecasting models, including machine learning, econometric, and time-series approaches, while assessing the role of big data sources such as Google Trends and social media analytics. Main Findings: The study highlights the growing significance of big data in tourism forecasting, particularly sources like Google Trends and social media analysis. It also identifies key challenges in integrating diverse data sources and critically assesses the comparative effectiveness and limitations of different forecasting approaches. Applications of the study: This study is valuable for tourism policymakers, industry stakeholders, and researchers in tourism analytics, economics, and business management. It supports improved forecasting models for strategic planning, resource allocation, and economic decision-making. Novelty/Originality of the study: Unlike previous reviews, this study provides a critical evaluation of different forecasting methods, emphasizing the comparative effectiveness of big data-driven approaches. It advances knowledge by exploring emerging trends and challenges in tourism demand forecasting.