Sequential Recommendation Using Convolutional Neural Networks

General Information:

Cover Page:

Outline:

Acronyms
Introduction
1 Sequential Recommender Systems
1.1 Introduction.
1.2 Recommender Systems
1.3 Data used by recommender systems
1.4 How do we provide data for recommender systems ?
1.4.1 Explicit feedback
1.4.2 Implicit feedback
1.4.3 Hybrid feedback
1.5 How does a recommender systems work?
1.6 Goals of Recommender Systems
1.7 Recommender Systems Types
1.7.1 Collaborative-Filtering Recommendation Systems
1.7.2 Content-Based Recommendation Systems
1.7.3 Hybrid-Based Recommendation Systems
1.7.4 Demographic-Based Recommendation Systems
1.7.5 Utility-Based Recommendation Systems
1.7.6 Knowledge-Based Recommendation Systems
1.8 Business Adoption and Applications
1.8.1 Recommendation Systems in e-Commerce
1.8.2 Recommendation Systems in Transportation
1.8.3 Recommendation Systems in the e-Health Domain
1.8.4 Recommendation Systems in Agriculture
1.8.5 Recommendation Systems in Media and Beyond
1.9 The Impact of Recommender Systems
1.10 Problems Associated With Recommender Systems
1.10.1 Limited content analysis
1.10.2 Over-specialisation
1.10.3 Cold start
1.10.4 Sparsity
1.10.5 Scalability
1.10.6 Synonymy
1.10.7 Abbreviation
1.10.8 Long tail
1.10.9 Black-box problem
1.11 Sequential Data
1.12 Sequential recommender systems (SRSS)
1.13 Difference Between Sequential Recommender Systems (SRSS) and Traditional Recommender Systems (RSS)
1.14 Representative Tasks
1.15 Inputs, Outputs, Computational Tasks
1.16 Specific Computational Tasks
1.16.1 Context adaptation
1.16.2 Trend Detection
1.16.3 Repeated Recommendation
1.16.4 Order constraints
1.17 Overview of Sequential Recommendation.
1.17.1 Experience-based behavior sequence
1.17.2 Transaction-based behavior sequence
1.17.3 Interaction-based behavior sequence
1.18 Sequential Recommender Systems approaches
1.18.1 Traditional Sequence Models for SRSS
1.18.2 Latent Representation Models for SRSS
1.18.3 Deep Neural Network Models for SRSS
1.19 Evaluation Protocols of Sequential Recommender Systems
1.19.1 Offline evaluation
1.19.2 Online evaluation
1.19.3 Making Reliable Choices
1.20 Conclusion
2 Convolutional Neural Networks
Introduction.
2.1 Artificial intelligence, Machine learning, and Deep learning
2.2 Machine Learning
2.2.1 Artificial Intelligence
2.2.2 Deep Learning
2.3 The Applications of Deep Learning
2.4 Artificial Neural Networks
2.4.1 Networks
2.4.2 Structure of a Neural Network
2.4.3 Neurons
2.4.4 Perceptron
2.4.5 Multi Layer Perceptron
2.4.6 Training Algorithms
2.5 Recurrent Neural Networks
2.6 Convolutional Neural Networks
2.6.1 kernels.
2.6.2 Convolution
2.6.3 Convolutional Neural Networks Architecture
2.6.4 Convolutional Neural Networks Types
2.7 Features Engineering
2.8 Layers
2.8.1 Convolution Layer
2.8.2 Pooling Layer
2.8.3 Fully Connected Layer
2.8.4 Loss Functions
2.9 Activation Functions
2.10 Convolutional Neural Networks for Sequence Data
2.10.1 1D pooling for sequence data
2.11 Why Deep Neural Networks for Recommendation?
2.12 Conclusion
3 Sequential Recommendation Using Convolutional Neural Networks
3.1 Introduction.
3.2 Time Series Forecasting
3.3 Convolutional Neural Networks for Time Series
3.4 Convolutional Neural Networks for Sequential Recommendation
3.4.1 What Are Word Embeddings?
3.4.2 Items Embedding (Word2Vec)
3.4.3 Supervised Learning with Sliding Windows
3.4.4 Network architecture
3.5 Experiments.
3.5.1 Last.fm Dataset
3.5.2 Python
3.5.3 Jupyter Notebook
3.5.3.1 Implementation
3.5.3.2 Keras
3.5.3.3 Evaluation Metrics
3.5.4 Results
3.6 Conclusion
Conclusion
Bibliography

Download The Thesis:

📥 تحميل الملف

For more
academic sources and references,
including theses and dissertations from Algerian universities,
, visit our main website.