Mathematical Model Applied for Hotel Recommendation System with Machine Learning

Abstract

the purpose of this paper is to promote the value of Albanian tourism creating a Hotel Recommendation System applying a Mathematical Model. The data of one hundred and one hotels, loaded from two excel files in CSV format are implemented in the Spyder IDE and processed by code, using Mathematical and Machine Learning knowledge. The code recommends ten best hotels as output. There is made a combination of Machine Learning methods and techniques with the concepts of probability, statistics, algebra and geometry. The main methodological approach taken in this study is Content-Based Filtering.

Introduction

I. INTRODUCTION

Albania is a small country, very little known in the world, but with great natural resources, which create the possibility of tourism development. This paper brings an innovation on how to promote the values carried by Albanian tourism and how to make the names of some of the most prestigious hotels on the Albanian coast known, using Machine Learning and mathematical knowledge, such as Bayes’ theorem, Conditional Probability, Cosine Similarity, etc.,

This paper serves the readers as a guide to orientate foreign tourists towards the Albanian coast, as well as a methodology that explains the creation of a code through the knowledge of the branches of mathematics and ML.

The rapid progress of technology and the increasing need of people to use it has resulted in a rise of data. The information spreads quickly and in a short time. The necessity of people to handle with this large amount of data prompted the advance of Artificial Intelligence (AI). According to the impacts of AI, the human society is adopting it in all areas of life [1].

Nowadays, people are becoming more and more addicted to technology. They spend most of the time on the phone, iPad, laptop, computer desktop, etc. They can shop there, have access to up-to-date information on events, communicate with each other, booking hotels, etc. So, there is a good idea, to promote tourism through code implemented with the Python programming language.

This paper presents a Machine-Learning Model for Hotel Recommendation System using knowledge of different areas of mathematics, including: probability and statistics, linear algebra, calculus, geometry. This code is like booking application, that people access to search hotels for holidays. The intelligent machine is placed at the service of human society, thanks to the algorithms, that allow it to process and generate new models based on data receiving from a huge database [2].

Machine Learning is a sub-field of Artificial Intelligence, which uses Recommendation Systems to recognize and matches the behavior of users, in order to train algorithms and create different models [3].

Algorithms learn from the activity of users (viewers, likes, dislikes, comments, ratings, etc.) and make hotel recommendations. The users are able to choose hotels they may like, grouped according to the features studied by algorithms. Furthermore, hotels from large datasets can be filtered using machine learning based autonomous tool recommendation movie system [4].

Additionally, Recommendation System can increase the amount of products and provide personalized service support to users by learning their previous behaviors and predicting their current preference for products [5].

Conclusion

Through a Mathematical Model we have created a simple Recommendation System as a type using data, based on our knowledge of probability, statistics, linear algebra, calculus, geometry. This model recommends to the user a list with ten hotels of Albania, from one hundred and one in total. We have used content-based filtering to create the code and to choose the movies based on the preferences and ratings of users. This model will help users interact with the page quickly and not take longer to find what they are looking for. With this code, we offer tourists the opportunity to get to know ten Albanian hotels that are at the top of the classification. As we also invite tourists to come and spend their holidays in the tourist spots of Albania. We also promote the values of Albanian tourism abroad.

References

[1] H. Herrmann, What’s next for responsible artificial intelligence: a way forward through responsible innovation, J.Helyon (2023). [2] M. C.-T. Tai, What is next for responsible artificial intelligence: a way forward through responsible innovation, Tzu Chi Medical Journal (2020). [3] L. Jianguo, Research progress of personalized recommendation system. adv. nat. sci., EURASIP Journal onWireless Communications and Networking (2009). [4] SonuAiren, Movie recommender system using parameter tuning of user and movie neighbourhood via coclustering, Procedia Computer Science (2023). [5] Q.Zhang, Artificial intelligence in recommender systems, complex intelligent systems, SpringerLink (2020). [6] F.Hdioud, Multi-criteria recommender systems based on multi-attribute decision making [7] W. McKinney, Python for data analysis, O’Reilly (2017) 1. [8] Ch.Hill, Learning scientific programming with python, Cambridge Core (2020) [9] J.Hunter, Matplotlib user guide, [10] Tutorial point. simply easy learning, tutorials point (2019) . [11] R.Manjula, Content based filtering techniques in recommendation system us-ing user preference, [12] E. Schubert, A triangle inequality for cosine similarity, arxiv (2021) [13] A. Sh.Tyagi, A machine learning based fashion recommendation system, Research Archive of Rising School (2023) 13. [14] F. Richi, Introduction to recommend system handbook, book chapter, International Journal of Innovations in Engineering and Technology (IJIET) (2011) 35. [15] A.Wibawa, Na¨?ve bayes classifier for journal quartile classification, International Journal of Recent contributions from Engineering, Science and IT (2019). [16] K. Kuter, Math 345 – probability, LibreText (2023) [17] M. F.Triola, ”Bayes’Theorem”. ”University of Washington”.

Copyright

Copyright © 2024 B. Shyti, A. Stergu, Dh. Valera . 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.