An Intelligent Travel Planning System for Indian Destinations Using Machine Learning Model

Abstract

With the emergence of the domestic tourism market in India, it has become a promising market to build a more intelligent travel planning system. Due to the intricacy of travel, the methods of planning trips have been found to be ineffective in handling the queries of the travel process. The proposed system will provide information regarding 370 tourist destinations in India, situated in 28 states and 8 Union Territories of the country. The proposed system will predict the tourist destinations to be feasible or not based on the budget of the users, type of travel, duration of the trip, and their likes and dislikes using the Random Forest Classifier, a machine learning approach, which can achieve a maximum accuracy of 99.66% using 3200 inputs in the test dataset. Apart from that, the chatbot that is powered by AI and has the ability to utilize large language models allows the chatbot to converse in real time. The ability of the chatbot to include a number of APIs in real time, such as the weather, is enabled by the addition of an automatic trip itinerary generator. The addition of a graphical interface that allows the user to search the destinations by maps makes it easier for the user to search the destinations. The addition of the sentiment analysis of the destinations by analyzing the reviews and rating the destinations according to the reviews is also made. The backend of the TravelWise system is developed by utilizing the Python Flask web application micro web framework. Apart from that, the SQLite database is utilized to store the destinations and itineraries information. The results obtained from the implementation of the TravelWise system reveal that it is a feasible, accurate, efficient, scalable, and user-friendly system that caters to the needs of both domestic and global tourists.

Introduction

India’s rapid digital growth has increased both opportunities and cybercrime risks, especially phishing attacks that target mobile users and exploit low digital literacy. Existing security systems often fail to detect modern, multilingual, and rapidly evolving phishing techniques. To address these limitations, the proposed system PhishShield is introduced as a free, multi-vector, AI-based phishing detection framework.

PhishShield combines multiple techniques: TF-IDF with Naive Bayes for analyzing text-based social engineering content, Decision Trees with OSINT (e.g., WHOIS, SSL checks) for URL verification, and explainable AI to provide transparent decision logic. It also includes a browser extension and web dashboard, real-time detection, and a human-in-the-loop feedback system for continuous improvement.

The literature review highlights that rule-based systems are slow and ineffective against zero-day attacks, while deep learning and transformer models, although accurate, are computationally heavy and lack explainability. Hence, PhishShield focuses on lightweight, fast, and interpretable machine learning methods suitable for real-world deployment.

The system’s goal is to detect phishing in real time by combining text analysis, URL structure evaluation, and OSINT-based validation in a parallel processing framework, ensuring higher accuracy, lower latency, and better user awareness through explainable outputs.

Conclusion

The TravelWise system represents an intelligent and comprehensive solution for modern travel planning by leveraging the potential of machine learning, artificial intelligence, and web technologies. The system is successful in providing users with recommendations for destinations, budget estimation, and the generation of itineraries based on their preferences. The Random Forest model ensures high prediction accuracy for the system. The integration of real-time services such as weather and mapping also increases the usability of the system. The inclusion of an AI chatbot also increases the user experience by providing interactive and user-friendly communication. In addition, the sentiment analysis of user reviews also increases the decision-making potential of the system by providing users with insights about the quality of the destinations. Overall, the TravelWise system represents the potential of AI-driven systems in transforming the traditional process of travel planning into an efficient and automated process. The system is also scalable and can be extended to include more features and real-time services.

References

[1] Anitha, S., Abinesh, B., Adhithya, R., Karthik, S., Sanjai Hari Kumar, R., & Thirukumaran, Y. (2025). AI powered trip planner. International Journal of Scientific Research and Technology, 2(2), 133–139. [2] Dhote, S., Gayakwad, N., Buwade, P., Bedre, R., & Sisodiya, P. S. (2025). AI-powered travel planner: Smart trip optimization. International Journal of Leading Research Publication, 6(3), 1–6. [3] Mote, A. V., Rajgure, N. K., Koparde, S., Munot, B., Keswad, T., & Nalawade, T. (2024). Implementation of AI-driven smart travel planner using A* algorithm. International Journal of Ingenious Research, Invention and Development, 3(5), 256–266. [4] Karkhile, P., Kavade, V., Gandhewar, A., Rai, O., & Karajgar, M. (2025). WanderSmart: Trip planning with AI. International Journal on Science and Technology, 16(2), 1–12. [5] Hermosa Del Vasto, P. M., & Arco Castro, M. L. (2024). Artificial intelligence (AI) in sustainable tourism: Bibliometric analysis. Cuadernos de Turismo, 53, 157–185. [6] Ravindra, S., Navya, P., Madhumitha, G., Aakash, V., & Sai Mani, M. (2025). AI trip planner for seamless travel experiences. Journal of Computer Science, 18(4), 95–103. [7] Talakoti, M., BalaRam, A., Jagli, D., Deepika, N., Priya, R. L., & Harshini, K. (2025). Trip tailor: AI-powered travel planning with itinerary generation and chatbot assistance. International Journal of Environmental Sciences, 11(4S), 920–929 [8] Chen, A., Ge, X., Fu, Z., Xiao, Y., & Chen, J. (2024). TravelAgent: An AI assistant for personalized travel planning. ArXiv. [9] Karmakar, P., Chaudhuri, S., Mallick, S., Gupta, M., Jana, A., & Ghosh, S. (2025). TripTide: A benchmark for adaptive travel planning under disruptions. arXiv. [10] Ling, E. C., Tussyadiah, I., Liu, A., & Stienmetz, J. (2024). Perceived intelligence of artificially intelligent assistants for travel: Scale development and validation. Journal of Travel Research. [11] Chaudhuri, S., Purkar, P., Raghav, R., Mallick, S., Gupta, M., Jana, A., & Ghosh, S. (2025). TripCraft: A benchmark for spatio-temporally fine grained travel planning. arXiv. [12] Štili?, A., Puška, A., & Nici?, M. (2024). The role of artificial intelligence in shaping the future of travel industry: A expert analysis of artificial intelligence-generated travel itineraries. Deturope: The Central European Journal of Regional Development and Tourism, 16(2), 57–79. [13] Xie, J., Zhang, K., Chen, J., Zhu, T., Lou, R., Tian, Y., Xiao, Y., & Su, Y. (2024). TravelPlanner: A benchmark for real-world planning with language agent. [14] Ning, Y., Liu, R., Wang, J., Chen, K., Li, W., Fang, J., Zheng, K., Tan, N., & Liu, H. (2025). DeepTravel: An end-to-end agentic reinforcement learning framework for autonomous travel planning agents. [15] Dalla Vecchia, A., Migliorini, S., Quintarelli, E., Gambini, M., & Belussi, A. (2024). Promoting sustainable tourism by recommending sequences of attractions with deep reinforcement learning. [16] Shafiq, Sridevi, Avula, Basi Reddy, Ahamed Shaik Khaleel, “Local Neighbour Spider Monkey Optimization-Based Resource Allocation in Cloud Computing Environment” Journal of Circuits, Systems and Computers, Vol. 35, No. 08, 2550490 (2026). [17] Sharma Pankaj, Jay Shankar, Shaheen, Ahamed Shaik Khaleel “An efficient cyber threat prediction using a novel artificial intelligence technique” Multimedia Tools and Applications, Vol. 83, pages 66757–66773, 2024.

Copyright

Copyright © 2026 Sadia Kauser, Syed Zabiuddin, Talha Khan, Dr. Shaik Khaleel Ahamed. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.