Evaluate the web-based tourism management by using the fuzzy expert system

Web-based tourism systems improve travel planning and destination discovery. However, they often face challenges in handling ambiguous user preferences and dynamic factors such as season, budget, and travel duration, reducing recommendation accuracy. However, current systems frequently struggle with ambiguous user choices, imprecise information, and unpredictable tourism variables such as season, time, and budget. The purpose of this research is to analyse and improve web-based tourist management by combining a fuzzy expert system with machine learning (ML) and optimization techniques to handle user preference uncertainty and increase suggestion accuracy. A tourism experience & recommendation insights dataset including online user reviews, ratings, and contextual information (travel season, duration, and location) is used. Preprocessing includes min max normalization. Feature extraction from numerical data is accomplished using Principal Component Analysis (PCA). The suggested Aquila with Fuzzy Random Forest (AFRF) method combines Fuzzy Random Forest (FRF) for tourist choice prediction, Fuzzy Analytic Hierarchy Process (FAHP) for dealing with uncertainty in ambiguous queries, and Aquila Optimization (AO) for fine-tuning fuzzy rules and membership functions. The proposed AFRF approach outperforms existing collaborative filtering methods in terms of recommendation accuracy. The AFRF method outperformed all current approaches by achieving superior results with 95.5% accuracy. It also shows better generalization and flexibility to different travel scenarios. The research reveals that combining fuzzy reasoning with ML and optimization increases the accuracy and personalization of web-based tourism recommendations, hence making tourism management systems more intelligent, efficient, and user-centered. Combining smart computing with traveler data boosts recommendation accuracy to over 95%. The new system better handles vague travel wishes like “nice weather” or “moderate budget”. It adapts recommendations to changing seasons, trip lengths, and costs for more personalization.