Garima, . and Swati, Gupta (2025) Optimizing LSTM Networks with Hippopotamus Optimization Algorithm for Enhanced Hotel Booking Recommendations Based on Hotel Reviews. Machine Learning, 26 (2). pp. 294-315. ISSN 0885-6125

Text fileserve.pdf Download (715kB)

Abstract

The fast growth of Europe’s hospitality business has given travellers an overwhelming number of hotel options, needing advanced recommendation systems. This study uses the Hippopotamus Optimisation Algorithm (HOA) to tune Long Short-Term Memory (LSTM) networks to improve hotel booking recommendations based on user evaluations. The LSTM network analyses massive volumes of unstructured textual data from hotel reviews to understand traveller attitudes and preferences and make personalised suggestions. The HOA optimises LSTM network hyperparameters for better prediction performance than standard techniques. A large European hotel review dataset shows that the proposed approach accurately recommends hotels that match user preferences. The final epoch of the proposed model had 0.2830 loss and 97.69% accuracy. Validation loss 0.3016, accuracy 93.37%. Despite its excellent training accuracy, the model’s constant validation accuracy and a bit higher validation loss may prevent generalisation and overfitting. The HOA-tuned LSTM model outperforms conventional optimisation methods, providing a more robust and trustworthy recommendation system. This research introduces an advanced optimisation technique that improves European travellers’ decision-making in intelligent tourism.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	11 Jul 2025 09:56
Last Modified:	11 Jul 2025 09:56
URI:	http://eprints.umsida.ac.id/id/eprint/16287

Actions (login required)

View Item