| Titre : | A Travel Recommendation System Based On Machine Learning Techniques |
| Auteurs : | Souria Salhaoui, Auteur ; Belkacem Abdelli, Directeur de thèse |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2024 |
| Format : | 1 vol. (77 p.) / ill., couv. ill. en coul / 30cm |
| Langues: | Français |
| Langues originales: | Français |
| Mots-clés: | Machine Learning , Recommendation System , Travel , Tourist , Web Application |
| Résumé : |
The travel recommendation system leverages technologies like machine learning, artificial intelligence,and big data analysis to understand user behavior and predict preferences, enablingpersonalized and effective travel suggestions. This system enhances traveler experiences byproviding tailored recommendations, saving time in finding suitable destinations and activities,and raising awareness of new tourist spots. Developing such a system poses technical andstrategic challenges but offers significant opportunities to improve traveler satisfaction.A dedicated travel web application has been developed based on these recommendation andmachine learning techniques. It allows users to discover major tourist attractions, access informationabout hotels and restaurants, and book various trips by connecting with travel agencies. The application also supports personal advertisements, expanding user choices when searching.Its key feature is recommending numerous tourist destinations based on user preferences,including details like city, price, cost, and time. Additionally, it offers quick search options forvarious user-required facilities. |
| Sommaire : |
References 11 General Introduction . . . . 12 0.1 context . . . . . . 12 0.2 Problematic . . . . . . 13 0.3 Objectives and solution . . . . 13 1 Recommendation System 14 1.1 Introduction . . . . . . . 14 1.2 Definition . . . . . . . 16 1.3 Recommendation Techniques . . . 17 1.3.1 Text Mining . . . . 18 1.3.2 KNN (K-Nearest Neighbor) . 19 1.3.3 Clustering . . . . . 20 1.3.4 Matrix Factorization . . 20 1.3.5 Neural Network . . . . 20 1.4 Research Trends of Recommendation System Techniques . . . . 21 1.5 Recommendation system based on deep learning methods: a systematic review and new directions . . . . . . 23 1.6 Social Implications . . . 23 1.7 related work . . . . . 26 1.8 conclustion . . . . . 28 2 Machine Learning and Deep Learning 29 2.1 Introduction . . . . 29 2.2 What is Artificial Intelligence? . . . . . 30 2.3 Machine Learning . . . . . . 31 2.3.1 definition ”1” . . 31 2.3.2 definition ”2” . . . .. 31 2.3.3 Types of Machine learning . 32 2.3.3.1 Supervised Learning . .. 32 2.3.3.2 Unsupervised Learning studies . 32 2.3.3.3 Reinforcement Learning(RL) . . 33 2.4 Deep Learning . . 34 2.4.1 Historical Trends in Deep Learning .. 34 2.4.2 Why Is Deep Learning So Successful? . . 35 2.4.3 Definitions of Deep Learning .. 35 2.4.3.1 Definitions”1” .. 35 2.4.3.2 Definitions”2”. 36 2.4.4 Overview of deep learning architectures . . 36 2.5 Artificial Intelligence [AI] Vs Machine Learning [ML] Vs Deep Learning [DL] 39 2.6 conclustion . . . 40 3 Conception 41 3.1 Introduction . . . . . 41 3.2 General Architecture of System .. . 41 3.3 Detailed Architecture of System .. . . . 43 3.3.1 Data Base . . . . . . 43 3.3.1.1 Data collection . .. 43 3.3.1.2 Data Preprocess . . 44 3.3.1.3 Study the most important data variables . . . . . . . . . . . 46 3.3.1.4 Types of Data for building recommendation systems . . . . . 48 3.3.1.5 Types of feedback in the database-based LightFM . . . . . . 48 3.3.2 Model Conseption numbre -1- RecommenderNET . .. 49 3.3.2.1 Data Understanding .. 49 3.3.2.2 Data Preprocessing . . . 49 3.3.2.3 Embedding Layer Class . . 49 3.3.2.4 RecommenderNet Model . . 49 3.3.2.5 Result . . . 50 3.3.2.6 Model Evaluation and training . .50 3.3.3 Model Conseption numbre -2- LightFM . 53 3.3.3.1 The technologies used by LightFM . . 53 3.3.3.2 Principle work of model lightFM . 54 3.3.3.3 The purpose of using LightFM . . 55 3.3.3.4 LightFM Python Library . 55 3.3.3.5 Model Evaluation . . 56 3.3.3.6 Model training . 57 3.3.4 Comparison between models : 59 3.4 Diagrams of Model Training .. . . 60 3.4.1 use case diagrame . 60 3.4.2 Sequence Diagram . 61 3.4.2.1 sequence diagram (sign in or sign up ). 61 3.4.2.2 sequence diagram (administrator sitting) . 62 3.4.2.3 Sequence diagram for travel web application . . . 63 3.4.3 diagram of class . . 64 3.5 conclution . . . . . . 65 4 Implementation 66 4.1 Introduction . . . .. . 66 4.1.1 HTML . . . . .. 66 4.1.2 CSS . . . . . . 67 4.1.3 PHP . . . . . . 67 4.1.4 XAMPP . . . . 67 4.1.5 Python . . . . 68 4.1.6 Jav4.1.7 Colaboratory . . . . 68 4.1.8 Kaggle . . . . . . . 69 4.2 Machine learning Model Implementation . 69 4.2.1 Dataset Import and Preparation .. 70 4.2.2 Training the ML Model . 76 4.2.3 The API server . . .. . 76 4.2.3.1 difintion . .. 76 4.3 Web Application Interface . . 78 4.3.1 front face . . . . . 78 4.3.1.1 Logine Page : 78 4.3.1.2 register page : . 79 4.3.2 Admin . . . . 80 4.3.2.1 Dashboard : . 80 4.3.2.2 Admin Profile : .. 80 4.3.2.3 Administrator settings Addvertisment : . 82 4.3.2.4 Administrator settings Places: . . . 84 4.3.2.5 Administrator settings Hotels: 87 4.3.2.6 Administrator settings Restaurent: .. 89 4.3.2.7 Administrator settings Reservation: . 91 4.3.3 user . . . . . . 92 4.3.3.1 Rating . .. 92 4.3.3.2 EDIT user Profile .. 93 4.3.4 home . . . . 94 4.3.5 Hotels Services . . . 99 4.3.6 Restaurant Services .. . 102 4.3.7 places Services . . . . 105 4.3.8 Recommendation score for different users . . . . . 109 4.4 conclustion . . . . . 112 General conclustion . . . . 113a Script . . . 68 |
| Type de document : | Mémoire master |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| MINF/876 | Mémoire master | bibliothèque sciences exactes | Consultable |
