Big Data Recommender Systems, Volume 2: Application Paradigms
- Length: 520 pages
- Edition: 1
- Language: English
- Publisher: The Institution of Engineering and Technology
- Publication Date: 2019-08-29
- ISBN-10: 1785619772
- ISBN-13: 9781785619779
- Sales Rank: #9527796 (See Top 100 Books)
First designed to generate personalized recommendations to users in the 90s, recommender systems apply knowledge discovery techniques to users’ data to suggest information, products, and services that best match their preferences. In recent decades, we have seen an exponential increase in the volumes of data, which has introduced many new challenges.
Divided into two volumes, this comprehensive set covers recent advances, challenges, novel solutions, and applications in big data recommender systems. Volume 2 covers a broad range of application paradigms for recommender systems over 22 chapters. Volume 1 contains 14 chapters addressing foundations, algorithms and architectures, approaches for big data, and trust and security measures.
Cover Title Copyright Contents Foreword 1 Introduction to big data recommender systems—volume 2 1.1 Background 1.2 About the book Acknowledgments References 2 Deep neural networks meet recommender systems 2.1 Preliminary 2.1.1 Introduction to recommender systems 2.1.2 Introduction to deep neural networks 2.2 Introducing nonlinearity to recommender systems 2.2.1 Deep neural generalization of collaborative filtering 2.2.2 Deep neural generalization of factorization machine 2.3 Representation learning for recommender systems 2.3.1 Representation learning with multilayer perceptron 2.3.2 Representation learning with autoencoder 2.3.3 Representation learning with convolutional neural network 2.3.4 Representation learning with Word2Vec 2.4 Sequence modelling for recommender systems 2.4.1 Session-based recommendations 2.4.2 Sequence-aware recommender systems 2.5 Deep hybrid models for recommender systems 2.6 Advanced topics 2.6.1 Metric learning 2.6.2 Generative adversarial networks 2.6.3 Neural autoregressive distribution estimator 2.7 Future challenges and conclusion References 3 Cold-start solutions for recommendation systems 3.1 Introduction 3.1.1 Recommendation approaches 3.2 Collaborative filtering 3.3 Active learning in recommender systems 3.4 Semantic-based recommender systems 3.5 Recommendation based on visual features 3.6 Personality-based recommender systems 3.7 Cross-domain recommender systems 3.8 Conclusion References 4 Performance metrics for traditional and context-aware big data recommender systems 4.1 Introduction 4.2 CARS—a brief overview 4.3 Evaluation of RSs 4.3.1 Evaluation metrics 4.4 Diversity and accuracy metrics used in CARS 4.4.1 How recommendation accuracy is measured in CARS? 4.4.2 Diversity measurement in CARS 4.5 How to choose an appropriate evaluation metrics? 4.6 Conclusion Acknowledgments References 5 Mining urban lifestyles: urban computing, human behavior and recommender systems 5.1 Mining shopping and mobility patterns 5.1.1 Prediction of shopping behavior with data sparsity 5.1.2 Adding contextual information to location data 5.1.3 Multi-perspective lifestyles 5.2 Data 5.3 Discovering shopping patterns 5.4 Mobility pattern extraction 5.4.1 Extracting cellular tower location types 5.4.2 Baseline methods 5.4.3 Characterizing mobility patterns 5.5 Predicting shopping behavior 5.5.1 Collective matrix factorization 5.6 Results 5.6.1 Prediction 5.6.2 Dual lifestyles 5.7 Discussion Acknowledgments References 6 Embedding principal component analysis inference in expert sensors for big data applications 6.1 Introduction 6.2 Related work 6.3 Principal component analysis: problem formulation 6.4 Workflow description 6.5 Embedded architecture 6.5.1 System-level architecture 6.5.2 PCA inference IP description 6.6 Experimental methodology 6.7 Experimental results 6.7.1 8- vs. 16-bit architectures 6.7.2 Hardware architecture vs. multicore approach 6.8 Conclusions Acknowledgments References 7 Decision support system to detect hidden pathologies of stroke: the CIPHER project 7.1 Introduction 7.2 Context: the CIPHER project 7.3 Decision support system 7.4 Validation 7.4.1 Data processing 7.4.2 Algorithm selection 7.4.3 First results 7.5 Conclusions and future works Acknowledgments References 8 Big data analytics for smart grids 8.1 Introduction 8.2 Dynamic energy management 8.2.1 Demand side management 8.2.2 Data-driven DEM 8.3 Failure protection 8.4 Load and price forecasting 8.4.1 Load classification 8.4.2 Short-term load forecasting 8.4.3 Renewable generation forecasting 8.4.4 Price forecasting 8.4.5 Predictive control for electric vehicles power demand 8.5 Efficient processing of extreme size of data 8.5.1 Avoidance of redundancies 8.5.2 Dimensionality reduction 8.5.3 Data summarization 8.5.4 MapReduce parallel processing 8.5.5 Distributed data mining 8.5.6 Efficient computing 8.5.7 Testbeds and platforms 8.6 Security and privacy issues in the smart grid 8.6.1 Privacy 8.6.2 Security 8.7 Conclusions References 9 Internet of Things and big data recommender systems to support Smart Grid 9.1 Introduction 9.2 IoT-supported SG—a communication perspective 9.3 Big data in SG 9.4 Making recommendations in SG 9.4.1 Load forecasting 9.4.2 Renewable energy forecasting 9.4.3 DR and energy management program 9.4.4 SG state estimation 9.5 Conclusion References 10 Recommendation techniques and their applications to the delivery of an online bibliotherapy 10.1 What is bibliotherapy? 10.2 Review of recommendation techniques 10.2.1 Stereotyping approach 10.2.2 Content-based filtering approach 10.2.3 Collaborative filtering approach 10.2.4 Co-occurrence recommendation approach 10.2.5 Graph-based approach 10.2.6 Global relevance approach 10.2.7 Hybrid approach 10.3 Reading recommendation in bibliotherapy 10.3.1 Categories of adolescent stress and reading articles 10.3.2 Unifying stress easing and reading interests for articles recommendation 10.3.3 Recommending procedure 10.4.1 The framework 10.4.2 System interfaces 10.5 Conclusion References 11 Stream processing in Big Data for e-health care 11.1 Introduction 11.2 Stream processing for low-latency analytics 11.2.1 Batch processing vs. stream processing 11.2.2 Challenges of stream processing 11.3 Real-time processors 11.3.1 Storm platform 11.3.2 Samza platform 11.3.3 Spark platform 11.4 Stream processing in e-health care 11.5 Conclusion References 12 How Hadoop and Spark benchmarking algorithms can improve remote health monitoring and data management platforms? 12.1 Introduction 12.2 E-care platform 12.2.1 Security and privacy challenges for healthcare applications 12.2.2 Problematic of E-care 12.3 Big data 12.4 Hadoop ecosystem 12.4.1 MapReduce 12.4.2 Spark 12.4.3 Other tools 12.5 Computational techniques 12.5.1 Machine learning techniques in medical field 12.5.2 Spark with machine learning techniques in medical field 12.6 Benchmarking 12.6.1 Benchmarking and big data 12.6.2 Types of benchmarking 12.7 Benchmarks in Hadoop and Spark 12.7.1 Amp Lab Benchmark 12.7.2 BigBench 12.7.3 BigDataBench 12.7.4 BigFrame 12.7.5 GridMix 12.7.6 HiBench 12.7.7 PigMix 12.7.8 SparkBench 12.7.9 Statistical Workload Injector for MapReduce 12.8 Benchmark comparison 12.9 Proposal 12.10 Conclusion References 13 Extracting and understanding user sentiments for big data analytics in big business brands 13.1 Introduction 13.2 Consumer behavior for understanding consumer sentiments 13.3 User sentiments 13.4 What is consumer sentiment? 13.4.1 Why sentiment analysis is required? 13.4.2 Need for neuromarketing based on psychology principles 13.4.3 How sentiment analysis can be correlated to consumer behavior? 13.5 The concept of neuromarketing 13.5.1 Neuromarketing techniques 13.5.2 How it works? 13.6 Big data analytics 13.6.1 Why big data for understanding of consumer behavior? 13.6.2 Big data analytics—next big thing 13.6.3 HADOOP 13.6.4 Master/Slave architecture of Hadoop 13.6.5 What is MapReduce? 13.7 Conclusion References Bibliography 14 A recommendation system for allocating video resources in multiple partitions 14.1 Introduction 14.2 Related work 14.3 Problem description 14.4 The proposed approach 14.5 Experimental evaluation 14.6 Conclusions and future work References 15 A mood-sensitive recommendation system in social sensing 15.1 Introduction 15.2 Related work 15.3 Problem formulation and terminology definition 15.4 Mood sensitive truth discovery 15.5 Evaluation 15.5.1 Datasets and preprocessing 15.5.2 Performance evaluation of MS-EM 15.6 Conclusion Acknowledgments References 16 The paradox of opinion leadership and recommendation culture in Chinese online movie reviews 16.1 Introduction 16.2 Related work on online leadership and recommendation 16.2.1 The rise of China 16.2.2 Opinion leadership 16.2.3 Recommendation system 16.2.4 Leadership for recommendations among social networks 16.3 Methodology 16.3.1 Data collection 16.3.2 Feature builder 16.3.3 Rule-mining functionality 16.3.4 Methodology outline 16.4 Leadership and recommendation analytics 16.4.1 Experimental setup 16.4.2 Feature statistics 16.4.3 Discovering leadership patterns 16.4.4 Discussion 16.5 Conclusion References 17 Real-time optimal route recommendations using MapReduce 17.1 Introduction 17.2 An overview of RRSs 17.2.1 Recommendation Systems 17.2.2 Route Recommendation Systems 17.2.3 Classification of RRSs 17.3 The requirements for RRS 17.3.1 Data requirements 17.3.2 Big or small Data? 17.3.3 Real-time issue 17.3.4 An architecture 17.3.5 The categories of requirements from another perspective 17.4 Summary References 18 Investigation of relationships between high-level user contexts and mobile application usage 18.1 Introduction 18.2 Related work 18.2.1 Investigation of mobile user's behavior 18.2.2 Collecting application usage logs 18.2.3 Collecting context information 18.3 Log-collection system 18.3.1 Initialization of the system 18.3.2 Questions about contexts 18.3.3 Collection of application usage logs 18.3.4 Game-based approach 18.4 Collected logs 18.4.1 High-level contexts 18.4.2 Application usage frequency 18.4.3 Tendency of application usage by time 18.5 Relationships between applications and contexts 18.5.1 Characteristic rules 18.5.2 Effect of single context 18.5.3 Effect of combination of contexts 18.6 Discussion 18.6.1 Impacts of collecting high-level contexts 18.6.2 Possible applications of high-level contexts 18.7 Conclusion References 19 Machine learning and stock recommendation 19.1 Introduction 19.2 Momentum and stock-return predictability 19.2.1 Momentum effects 19.2.2 Jegadeesh–Titman (JT) momentum strategy 19.2.3 52-Week high (52WH) momentum strategy 19.3 Machine-learning-based momentum strategy 19.3.1 Feature engineering 19.3.2 Labelling 19.3.3 Training and testing 19.3.4 Portfolio formation 19.4 Empirical results 19.4.1 Classification accuracy 19.4.2 Portfolio performance 19.5 Machine-learning-based stock recommendation 19.5.1 Design of the model 19.5.2 Empirical results 19.6 Conclusion References 20 The role of smartphone in recommender systems: opportunities and challenges 20.1 Introduction 20.2 Silence is also evidence: interpret dwell time 20.2.1 Modeling the silence behavior 20.2.2 Modeling the dwell time 20.2.3 Model inference and application 20.3 App recommendation: contest between temptation and satisfaction 20.3.1 Failure of recommendation 20.3.2 Modeling the contest–-actual-tempting model 20.3.3 Insights of the model 20.4 POI recommendation: geographical, social and temporal 20.4.1 Geographical influence 20.4.2 Social influence 20.4.3 Temporal influence 20.5 Conclusion References 21 Graph-based recommendations: from data representation to feature extraction and application 21.1 Introduction 21.2 Background and related work 21.2.1 Graph-based recommender systems 21.2.2 Feature engineering for recommendations 21.3 Graph-based data modeling for recommendation systems 21.3.1 The structure of a recommender system dataset 21.3.2 Transforming tabular into graph-based representation 21.3.3 Distilling graph features 21.4 Experimental setting and datasets 21.4.1 Dataset I—Last.fm 21.4.2 Dataset II—Yelp (from RecSys-2013) 21.4.3 Dataset III—Yelp II (with social links) 21.4.4 Dataset IV—Movielens 21.4.5 Summary of the datasets, features, and metrics 21.5 Results and analysis 21.5.1 Case study I: overall contribution of the graph-based approach 21.5.2 Case study II: different graph schemes and their impact on recommendations 21.6 Discussion and conclusions 21.6.1 Discussion 21.6.2 Conclusions and future work References 22 AmritaDGA: a comprehensive data set for domain generation algorithms (DGAs) based domain name detection systems and application of deep learning 22.1 Introduction 22.2 Related methods toward deep learning-based DGA detection and categorization 22.3 Summary of submitted systems of DMD 2018 shared task 22.4 Domain name system (DNS) 22.5 Domain fluxing 22.6 Scalable framework 22.7 Real-time DNS data collection in an Ethernet LAN 22.8 Description of data set 22.9 Deep learning 22.9.1 Recurrent structures 22.9.2 Convolutional neural network 22.10 AmritaDGANet 22.11 AmritaDGA data analysis, results and observations 22.12 Conclusion and future work Acknowledgments References Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.