← Back to Publications List

The Role of Big Data Analytics in Predicting Seasonal Tourist Inflow Trends for the Sylhet and Chittagong Divisions

Students & Supervisors

Student Authors
Tamim Hasan Apurbo
Bachelor of Science in Computer Science & Engineering, FST
Mahdi Hassan Noor Asif
Bachelor of Science in Computer Science & Engineering, FST
Istiak Ahmad
Bachelor of Science in Computer Science & Engineering, FST
Supervisors
Md. Mortuza Ahmmed
Associate Professor, Faculty, FST

Abstract

Tourism in Bangladesh has been reported to be very seasonal and heavily reliant on the Sylhet and Chittagong division where the pattern of tourism is affected by the weather and culture. Predictive modeling at a regional level has not been much used, although some national statistics provided by the Bangladesh Tourism Board (BTB) show a general trend. The lack of accurate seasonal forecasting is a constraint on making data-driven decisions on accommodation, transport, and sustainable destination management. This paper bridges that gap by applying big data analytics to simulate and predict seasonal tourist inflows using both official arrival data and proxy web signals as indicators of search and booking activity. Objective and Methodology: This paper will use big data analytics to forecast seasonal patterns of tourist inflows in Sylhet and Chittagong, based on combined data from the Bangladesh Tourism Board, climate indicators, and web search query indices. The data of 1995-2024 was analyzed by time-series decomposition, correlation heatmap exploration, and regression modeling. The analytical pipelines have been written in Python and R in order to calculate seasonal, climatic, and mobility indicators and to represent tendencies in inflows. Results: The results indicate that there were strong positive relationships between winter-temperature reductions and inflow-volume increases, but the number of visitors was influenced negatively by monsoon rainfall. Regression analysis showed the predictive fit (R2 > 0.85) to be significant in predicting the combined climatic and web search features. The trend analysis indicated regular peaks between October and March, which implies that winter tourism is more common. The tourism authorities can use the results to enhance seasonal planning and marketing, and more particularly, the sustainable development of tourism in Bangladesh can be improved by the policy formulation based on the evidence-based policy design.

Keywords

Tourism Forecasting Seasonal Variability Big Data Analytics Proxy Indicators Climate Sensitivity.

Publication Details

  • Type of Publication:
  • Conference Name: RMSTU National Tourism Conference 2026
  • Date of Conference: 16/01/2026 - 16/01/2026
  • Venue: Rangamati Science and Technology University (RMSTU)
  • Organizer: Rangamati Science & Technology University (RMSTU) in collaboration with Bangladesh Tourism Board (BTB)
View on Publisher