Abstract :

Indonesia S Tourism Industry Has Expanded Rapidly, Leading To The Generation Of Extensive Data On Traveller Interests, Destinations, Costs, And Trip Durations. However, Traditional Recommendation Approaches Such As Those Offered By Travel Agencies Or Guidebooks Often Depend On Generalized Assumptions And Lack Personalization, Resulting In Suggestions That May Not Fully Match Individual Preferences. To Overcome These Shortcomings, This Research Presents A Hybrid Learning-based Travel Recommendation System That Utilizes Indonesian Tourism Datasets To Provide Tailored Suggestions. The Study Compares Several Classification And Regression Tree (CART)-based Techniques, Including Linear Logistic Regression (LLR), Support Vector Machine (SVM), And Random Forest (RF). The Proposed Approach, Neuro Tree Net (NTN), Merges An Artificial Neural Network (ANN) With An Extra Trees (ET) Model, Enabling The System To Effectively Learn Complex And Nonlinear Relationships Within Tourism Data. Experimental Evaluations Reveal That This Hybrid Model Delivers Higher Prediction Accuracy Than Conventional Single-model Methods. Users Can Define Their Preferences, Such As Budget Constraints, Available Travel Time, And Minimum Ratings, To Receive Customized Destination Recommendations. The System S Backend Manages Data Preprocessing, Model Training, And Predictions Using Tools Like Pandas, Scikit-learn, Keras, And Matplotlib, While An Interactive Interface Developed With Django Displays The Results. In Addition To Improving Recommendation Accuracy, The System Also Provides Valuable Insights Into Tourism Trends, Helping Users Plan Their Trips More Effectively And Make Well-informed Decisions.

Published:

09-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

2138-2147

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite