Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62084
Volume:
10 |
4 |
April 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Department of Computer Science & Engineering and Data Science
Bhagwan Parshuram Institute of Technology, Delhi
Department of Computer Science & Engineering and Data Science
Bhagwan Parshuram Institute of Technology, Delhi
Department of Computer Science & Engineering and Data Science
Bhagwan Parshuram Institute of Technology, Delhi
Department of Computer Science & Engineering and Data Science
Bhagwan Parshuram Institute of Technology, Delhi
Department of Computer Science & Engineering and Data Science
Bhagwan Parshuram Institute of Technology, Delhi
The exponential growth of digital travel platforms has introduced new challenges in delivering personalised, budget-aware accommodation recommendations. This paper presents an AI-powered hotel recommendation and travel planning system integrating a React Native mobile frontend with a FastAPI backend and the LLaMA 3.3 70B large language model via the Groq API. A rule-based budget analysis engine decomposes financial constraints across accommodation, transportation, and food categories. Evaluation demonstrates high natural language parsing accuracy (91.4%), budget feasibility classification (88.7%), and hotel recommendation Precision@5 (85.2%) based on experimental evaluation, with an average response time of 2.3 seconds and a System Usability Scale score of 81.3. The modular four-tier architecture supports extensibility toward real-time APIs, user authentication, and ML-driven personalisation.
KEYWORDS
This paper has presented the design, implementation, and empirical evaluation of an AI-powered hotel recommendation and travel planning system. The system’s three primary technical contributions are: (i) a LLaMA 3.3 70B-powered natural language query parser achieving 91.4% parameter extraction accuracy without domain-specific fine-tuning; (ii) a rule-based budget feasibility engine classifying trip affordability with 88.7% accuracy; and (iii) a composite hotel ranking algorithm achieving Precision@5 of 85.2%. Evaluation results confirm that the system significantly outperforms keyword-based baseline approaches on natural language understanding and feature completeness. The System Usability Scale score of 81.3 indicates strong acceptance of the conversational interface paradigm. The modular four-tier architecture depicted in Fig. 1 ensures that each component can be independently upgraded or replaced as more capable technologies emerge. The system development follows an iterative and modular software engineering approach aligned with Software Project Management principles.
[1] D. Patel et al., “A Comprehensive Review of Hotel Recommendation Systems Using Reviews and AI,” International Journal of Scientific Research in Computer Science, 2026. https://ijsrcseit.com/index.php/home/article/view/CSEIT261215/CSEIT261215 [2] L. Aravani et al., “A Natural Language Processing Framework for Hotel Recommendation Based on Users’ Text Reviews,” arXiv, 2024. https://arxiv.org/abs/2408.00716 [3] M. Remountakis et al., “ChatGPT and Persuasive Technologies for Personalized Hotel Recommendations,” arXiv, 2023. https://arxiv.org/abs/2307.14298 [4] S. Patil et al., “Hotel Recommendation System Using Deep Learning and Contextual Analysis,” 2025. https://journal.ardigitech.in/admin/papers/67e2a3c921a54.pdf [5] I. Saifudin et al., “Systematic Literature Review on Recommender Systems,” 2024. https://eclass.hmu.gr/modules/document/file.php/TP374/Homework/1st%20Homework%20-%20SLR%20evaluation/Systematic%20Literature%20Reviews/2024%20-%20Systematic%20Literature%20Review%20on%20Recommender%20Systems.pdf [6] P. Pang et al., “Hotel Recommendation System Using Machine Learning Techniques,” 2023. https://eprints.utar.edu.my/5997/1/fyp_IA_2023_PCC.pdf
Publication Date
4/30/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
3
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...