Recommender System with Machine Learning and Artificial Intelligence
Description
This book is a multi-disciplinary effort that involves world-wide experts from diverse fields, such as artificial intelligence, human computer interaction, information technology, data mining, statistics, adaptive user interfaces, decision support systems, marketing, and consumer behavior. It comprehensively covers the topic of recommender systems, which provide personalized recommendations of items or services to the new users based on their past behavior. Recommender system methods have been adapted to diverse applications including social networking, movie recommendation, query log mining, news recommendations, and computational advertising.
This book synthesizes both fundamental and advanced topics of a research area that has now reached maturity. Recommendations in agricultural or healthcare domains and contexts, the context of a recommendation can be viewed as important side information that affects the recommendation goals. Different types of context such as temporal data, spatial data, social data, tagging data, and trustworthiness are explored. This book illustrates how this technology can support the user in decision-making, planning and purchasing processes in agricultural & healthcare sectors.
More details
Other editions
Additional editions
Persons
Sachi Nandan Mohanty received his PhD from IIT Kharagpur, India in 2015 and is now at ICFAI Foundation for Higher Education, Hyderabad, India.
Jyotir Moy Chatterjee is working as an Assistant Professor (IT) at Lord Buddha Education Foundation, Kathmandu, Nepal. He has completed M.Tech in Computer Science & Engineering from Kalinga Institute of Industrial Technology, Bhubaneswar, India.
Sarika Jain obtained her PhD in the field of Knowledge Representation in Artificial Intelligence in 2011. She has served in the field of education for over 18 years and is currently in service at the National Institute of Technology, Kurukshetra.
Ahmed A. Elngar is the Founder and Head of Scientific Innovation Research Group (SIRG) and Assistant Professor of Computer Science at the Faculty of Computers and Information, Beni-Suef University, Egypt.
Priya Gupta is working as an Assistant Professor in the Department of Computer Science at Maharaja Agrasen College, University of Delhi. Her Doctoral Degree is from BIT (Mesra), Ranchi.
Content
Preface xix
Acknowledgment xxiii
Part 1: Introduction to Recommender Systems 1
1 An Introduction to Basic Concepts on Recommender Systems 3
Pooja Rana, Nishi Jain and Usha Mittal
1.1 Introduction 4
1.2 Functions of Recommendation Systems 5
1.3 Data and Knowledge Sources 6
1.4 Types of Recommendation Systems 8
1.4.1 Content-Based 8
1.4.1.1 Advantages of Content-Based Recommendation 11
1.4.1.2 Disadvantages of Content-Based Recommendation 11
1.4.2 Collaborative Filtering 12
1.5 Item-Based Recommendation vs. User-Based Recommendation System 14
1.5.1 Advantages of Memory-Based Collaborative Filtering 15
1.5.2 Shortcomings 16
1.5.3 Advantages of Model-Based Collaborative Filtering 17
1.5.4 Shortcomings 17
1.5.5 Hybrid Recommendation System 17
1.5.6 Advantages of Hybrid Recommendation Systems 18
1.5.7 Shortcomings 18
1.5.8 Other Recommendation Systems 18
1.6 Evaluation Metrics for Recommendation Engines 19
1.7 Problems with Recommendation Systems and Possible Solutions 20
1.7.1 Advantages of Recommendation Systems 23
1.7.2 Disadvantages of Recommendation Systems 24
1.8 Applications of Recommender Systems 24
References 25
2 A Brief Model Overview of Personalized Recommendation to Citizens in the Health-Care Industry 27
Subhasish Mohapatra and Kunal Anand
2.1 Introduction 28
2.2 Methods Used in Recommender System 29
2.2.1 Content-Based 29
2.2.2 Collaborative Filtering 32
2.2.3 Hybrid Filtering 33
2.3 Related Work 33
2.4 Types of Explanation 34
2.5 Explanation Methodology 35
2.5.1 Collaborative-Based 36
2.5.2 Content-Based 36
2.5.3 Knowledge and Utility-Based 37
2.5.4 Case-Based 37
2.5.5 Demographic-Based 38
2.6 Proposed Theoretical Framework for Explanation-Based Recommender System in Health-Care Domain 39
2.7 Flowchart 39
2.8 Conclusion 41
References 41
3 2Es of TIS: A Review of Information Exchange and Extraction in Tourism Information Systems 45
Malik M. Saad Missen, Mickaël Coustaty, Hina Asmat, Amnah Firdous, Nadeem Akhtar, Muhammad Akram and V. B. Surya Prasath
3.1 Introduction 46
3.2 Information Exchange 49
3.2.1 Exchange of Tourism Objects Data 49
3.2.1.1 Semantic Clashes 50
3.2.1.2 Structural Clashes 50
3.2.2 Schema.org-The Future 51
3.2.2.1 Schema.org Extension Mechanism 52
3.2.2.2 Schema.org Tourism Vocabulary 52
3.2.3 Exchange of Tourism-Related Statistical Data 53
3.3 Information Extraction 55
3.3.1 Opinion Extraction 56
3.3.2 Opinion Mining 57
3.4 Sentiment Annotation 57
3.4.1 SentiML 58
3.4.1.1 SentiML Example 58
3.4.2 OpinionMiningML 59
3.4.2.1 OpinionMiningML Example 60
3.4.3 EmotionML 61
3.4.3.1 EmotionML Example 61
3.5 Comparison of Different Annotations Schemes 62
3.6 Temporal and Event Extraction 64
3.7 TimeML 65
3.8 Conclusions 67
References 67
Part 2: Machine Learning-Based Recommender Systems 71
4 Concepts of Recommendation System from the Perspective of Machine Learning 73
Sumanta Chandra Mishra Sharma, Adway Mitra and Deepayan Chakraborty
4.1 Introduction 73
4.2 Entities of Recommendation System 74
4.2.1 User 74
4.2.2 Items 75
4.2.3 Action 75
4.3 Techniques of Recommendation 76
4.3.1 Personalized Recommendation System 77
4.3.2 Non-Personalized Recommendation System 77
4.3.3 Content-Based Filtering 77
4.3.4 Collaborative Filtering 78
4.3.5 Model-Based Filtering 80
4.3.6 Memory-Based Filtering 80
4.3.7 Hybrid Recommendation Technique 81
4.3.8 Social Media Recommendation Technique 82
4.4 Performance Evaluation 82
4.5 Challenges 83
4.5.1 Sparsity of Data 84
4.5.2 Scalability 84
4.5.3 Slow Start 84
4.5.4 Gray Sheep and Black Sheep 84
4.5.5 Item Duplication 84
4.5.6 Privacy Issue 84
4.5.7 Biasness 85
4.6 Applications 85
4.7 Conclusion 85
References 85
5 A Machine Learning Approach to Recommend Suitable Crops and Fertilizers for Agriculture 89
Govind Kumar Jha, Preetish Ranjan and Manish Gaur
5.1 Introduction 90
5.2 Literature Review 91
5.3 Methodology 93
5.4 Results and Analysis 96
5.5 Conclusion 97
References 98
6 Accuracy-Assured Privacy-Preserving Recommender System Using Hybrid-Based Deep Learning Method 101
Abhaya Kumar Sahoo and Chittaranjan Pradhan
6.1 Introduction 102
6.2 Overview of Recommender System 103
6.3 Collaborative Filtering-Based Recommender System 106
6.4 Machine Learning Methods Used in Recommender System 107
6.5 Proposed RBM Model-Based Movie Recommender System 110
6.6 Proposed CRBM Model-Based Movie Recommender System 113
6.7 Conclusion and Future Work 115
References 118
7 Machine Learning-Based Recommender System for Breast Cancer Prognosis 121
G. Kanimozhi, P. Shanmugavadivu and M. Mary Shanthi Rani
7.1 Introduction 122
7.2 Related Works 124
7.3 Methodology 125
7.3.1 Experimental Dataset 125
7.3.2 Feature Selection 127
7.3.3 Functional Phases of MLRS-BC 128
7.3.4 Prediction Algorithms 129
7.4 Results and Discussion 131
7.5 Conclusion 138
Acknowledgment 139
References 139
8 A Recommended System for Crop Disease Detection and Yield Prediction Using Machine Learning Approach 141
Pooja Akulwar
8.1 Introduction 142
8.2 Machine Learning 143
8.2.1 Overview 143
8.2.2 Machine Learning Algorithms 145
8.2.3 Machine Learning Methods 146
8.2.3.1 Artificial Neural Network 146
8.2.3.2 Support Vector Machines 146
8.2.3.3 K-Nearest Neighbors (K-NN) 147
8.2.3.4 Decision Tree Learning 147
8.2.3.5 Random Forest 148
8.2.3.6 Gradient Boosted Decision Tree (GBDT) 149
8.2.3.7 Regularized Greedy Forest (RGF) 150
8.3 Recommender System 151
8.3.1 Overview 151
8.4 Crop Management 153
8.4.1 Yield Prediction 153
8.4.2 Disease Detection 154
8.4.3 Weed Detection 156
8.4.4 Crop Quality 159
8.5 Application-Crop Disease Detection and Yield Prediction 159
References 162
Part 3: Content-Based Recommender Systems 165
9 Content-Based Recommender Systems 167
Poonam Bhatia Anand and Rajender Nath
9.1 Introduction 167
9.2 Literature Review 168
9.3 Recommendation Process 172
9.3.1 Architecture of Content-Based Recommender System 172
9.3.2 Profile Cleaner Representation 175
9.4 Techniques Used for Item Representation and Learning User Profile 176
9.4.1 Representation of Content 176
9.4.2 Vector Space Model Based on Keywords 177
9.4.3 Techniques for Learning Profiles of User 179
9.4.3.1 Probabilistic Method 179
9.4.3.2 Rocchio's and Relevance Feedback Method 180
9.4.3.3 Other Methods 181
9.5 Applicability of Recommender System in Healthcare and Agriculture 182
9.5.1 Recommendation System in Healthcare 182
9.5.2 Recommender System in Agriculture 184
9.6 Pros and Cons of Content-Based Recommender System 186
9.7 Conclusion 187
References 188
10 Content (Item)-Based Recommendation System 197
R. Balamurali
10.1 Introduction 198
10.2 Phases of Content-Based Recommendation Generation 198
10.3 Content-Based Recommendation Using Cosine Similarity 199
10.4 Content-Based Recommendations Using Optimization Techniques 204
10.5 Content-Based Recommendation Using the Tree Induction Algorithm 208
10.6 Summary 212
References 213
11 Content-Based Health Recommender Systems 215
Soumya Prakash Rana, Maitreyee Dey, Javier Prieto and Sandra Dudley
11.1 Introduction 216
11.2 Typical Health Recommender System Framework 217
11.3 Components of Content-Based Health Recommender System 218
11.4 Unstructured Data Processing 220
11.5 Unsupervised Feature Extraction & Weighting 221
11.5.1 Bag of Words (BoW) 221
11.5.2 Word to Vector (Word2Vec) 222
11.5.3 Global Vectors for Word Representations (Glove) 222
11.6 Supervised Feature Selection & Weighting 222
11.7 Feedback Collection 225
11.7.1 Medication & Therapy 225
11.7.2 Healthy Diet Plan 225
11.7.3 Suggestions 225
11.8 Training & Health Recommendation Generation 226
11.8.1 Analogy-Based ML in CBHRS 227
11.8.2 Specimen-Based ML in CBHRS 227
11.9 Evaluation of Content Based Health Recommender System 228
11.10 Design Criteria of CBHRS 229
11.10.1 Micro-Level & Lucidity 230
11.10.2 Interactive Interface 230
11.10.3 Data Protection 230
11.10.4 Risk & Uncertainty Management 231
11.10.5 Doctor-in-Loop (DiL) 231
11.11 Conclusions and Future Research Directions 231
References 233
12 Context-Based Social Media Recommendation System 237
R. Sujithra Kanmani and B. Surendiran
12.1 Introduction 237
12.2 Literature Survey 240
12.3 Motivation and Objectives 241
12.3.1 Architecture 241
12.3.2 Modules 242
12.3.3 Implementation Details 243
12.4 Performance Measures 243
12.5 Precision 243
12.6 Recall 243
12.7 F- Measure 244
12.8 Evaluation Results 244
12.9 Conclusion and Future Work 247
References 248
13 Netflix Challenge-Improving Movie Recommendations 251
Vasu Goel
13.1 Introduction 251
13.2 Data Preprocessing 252
13.3 MovieLens Data 253
13.4 Data Exploration 255
13.5 Distributions 256
13.6 Data Analysis 257
13.7 Results 265
13.8 Conclusion 266
References 266
14 Product or Item-Based Recommender System 269
Jyoti Rani, Usha Mittal and Geetika Gupta
14.1 Introduction 270
14.2 Various Techniques to Design Food Recommendation System 271
14.2.1 Collaborative Filtering Recommender Systems 271
14.2.2 Content-Based Recommender Systems (CB) 272
14.2.3 Knowledge-Based Recommender Systems 272
14.2.4 Hybrid Recommender Systems 273
14.2.5 Context Aware Approaches 273
14.2.6 Group-Based Methods 273
14.2.7 Different Types of Food Recommender Systems 273
14.3 Implementation of Food Recommender System Using Content-Based Approach 276
14.3.1 Item Profile Representation 277
14.3.2 Information Retrieval 278
14.3.3 Word2vec 278
14.3.4 How are word2vec Embedding's Obtained? 278
14.3.5 Obtaining word2vec Embeddings 279
14.3.6 Dataset 280
14.3.6.1 Data Preprocessing 280
14.3.7 Web Scrapping For Food List 280
14.3.7.1 Porter Stemming All Words 280
14.3.7.2 Filtering Our Ingredients 280
14.3.7.3 Final Data Frame with Dishes and Their Ingredients 281
14.3.7.4 Hamming Distance 281
14.3.7.5 Jaccard Distance 282
14.4 Results 282
14.5 Observations 283
14.6 Future Perspective of Recommender Systems 283
14.6.1 User Information Challenges 283
14.6.1.1 User Nutrition Information Uncertainty 283
14.6.1.2 User Rating Data Collection 284
14.6.2 Recommendation Algorithms Challenges 284
14.6.2.1 User Information Such as Likes/ Dislikes Food or Nutritional Needs 284
14.6.2.2 Recipe Databases 284
14.6.2.3 A Set of Constraints or Rules 285
14.6.3 Challenges Concerning Changing Eating Behavior of Consumers 285
14.6.4 Challenges Regarding Explanations and Visualizations 286
14.7 Conclusion 286
Acknowledgements 287
References 287
Part 4: Blockchain & IoT-Based Recommender Systems 291
15 A Trust-Based Recommender System Built on IoT Blockchain Network With Cognitive Framework 293
S. Porkodi and D. Kesavaraja
15.1 Introduction 294
15.1.1 Today and Tomorrow 294
15.1.2 Vision 294
15.1.3 Internet of Things 294
15.1.4 Blockchain 295
15.1.5 Cognitive Systems 296
15.1.6 Application 296
15.2 Technologies and its Combinations 297
15.2.1 IoT-Blockchain 297
15.2.2 IoT-Cognitive System 298
15.2.3 Blockchain-Cognitive System 298
15.2.4 IoT-Blockchain-Cognitive System 298
15.3 Crypto Currencies With IoT-Case Studies 299
15.4 Trust-Based Recommender System 299
15.4.1 Requirement 299
15.4.2 Things Management 302
15.4.3 Cognitive Process 303
15.5 Recommender System Platform 304
15.6 Conclusion and Future Directions 307
References 307
16 Development of a Recommender System HealthMudra Using Blockchain for Prevention of Diabetes 313
Rashmi Bhardwaj and Debabrata Datta
16.1 Introduction 314
16.2 Architecture of Blockchain 317
16.2.1 Definition of Blockchain 318
16.2.2 Structure of Blockchain 318
16.3 Role of HealthMudra in Diabetic 322
16.4 Blockchain Technology Solutions 324
16.4.1 Predictive Models of Health Data Analysis 325
16.5 Conclusions 325
References 326
Part 5: Healthcare Recommender Systems 329
17 Case Study 1: Health Care Recommender Systems 331
Usha Mittal, Nancy Singla and Geetika Gupta
17.1 Introduction 332
17.1.1 Health Care Recommender System 332
17.1.2 Parkinson's Disease: Causes and Symptoms 333
17.1.3 Parkinson's Disease: Treatment and Surgical Approaches 334
17.2 Review of Literature 335
17.2.1 Machine Learning Algorithms for Parkinson's Data 337
17.2.2 Visualization 340
17.3 Recommender System for Parkinson's Disease (PD) 341
17.3.1 How Will One Know When Parkinson's has Progressed? 342
17.3.2 Dataset for Parkinson's Disease (PD) 342
17.3.3 Feature Selection 343
17.3.4 Classification 343
17.3.4.1 Logistic Regression 343
17.3.4.2 K Nearest Neighbor (KNN) 343
17.3.4.3 Support Vector Machine (SVM) 344
17.3.4.4 Decision Tree 344
17.3.5 Train and Test Data 344
17.3.6 Recommender System 344
17.4 Future Perspectives 345
17.5 Conclusions 346
References 348
18 Temporal Change Analysis-Based Recommender System for Alzheimer Disease Classification 351
S. Naganandhini, P. Shanmugavadivu and M. Mary Shanthi Rani
18.1 Introduction 352
18.2 Related Work 352
18.3 Mechanism of TCA-RS-AD 353
18.4 Experimental Dataset 354
18.5 Neural Network 357
18.6 Conclusion 370
References 370
19 Regularization of Graphs: Sentiment Classification 373
R.S.M. Lakshmi Patibandla
19.1 Introduction 373
19.2 Neural Structured Learning 374
19.3 Some Neural Network Models 375
19.4 Experimental Results 377
19.4.1 Base Model 379
19.4.2 Graph Regularization 382
19.5 Conclusion 383
References 384
20 TSARS: A Tree-Similarity Algorithm-Based Agricultural Recommender System 387
Madhusree Kuanr, Puspanjali Mohapatra and Sasmita Subhadarsinee Choudhury
20.1 Introduction 388
20.2 Literature Survey 390
20.3 Research Gap 393
20.4 Problem Definitions 393
20.5 Methodology 393
20.6 Results & Discussion 394
20.6.1 Performance Evaluation 394
20.6.2 Time Complexity Analysis 396
20.7 Conclusion & Future Work 397
References 399
21 Influenceable Targets Recommendation Analyzing Social Activities in Egocentric Online Social Networks 401
Soumyadeep Debnath, Dhrubasish Sarkar and Dipankar Das
21.1 Introduction 402
21.2 Literature Review 403
21.3 Dataset Collection Process with Details 404
21.3.1 Main User's Activities Data 405
21.3.2 Network Member's Activities Data 405
21.3.3 Tools and Libraries for Data Collection 405
21.3.4 Details of the Datasets 406
21.4 Primary Preprocessing of Data 406
21.4.1 Language Detection and Translation 406
21.4.2 Tagged Tweeters Collection 407
21.4.3 Textual Noise Removal 407
21.4.4 Textual Spelling and Correction 407
21.5 Influence and Social Activities Analysis 407
21.5.1 Step 1: Targets Selection From OSMs 408
21.5.2 Step 3: Categories Classification of Social Contents 408
21.5.3 Step 4: Sentiments Analysis of Social Contents 408
21.6 Recommendation System 409
21.6.1 Secondary Preprocessing of Data 409
21.6.2 Recommendation Analyzing Contents of Social Activities 411
21.7 Top Most Influenceable Targets Evaluation 413
21.8 Conclusion 414
21.9 Future Scope 415
References 415
Index 417
1
An Introduction to Basic Concepts on Recommender Systems
Pooja Rana, Nishi Jain and Usha Mittal*
Department of Computer Science and Engineering, Lovely Professional University, Phagwara, India
Abstract
In today's world, we find a wide range of possibilities of any search that we do online and we might find difficulties in choosing what we actually need. To address these issues, recommendation System plays a major role. A recommender system is a filtering system that filters the data using different algorithms and recommends the most relevant data to the user. For instance, a recommender system for e-commerce requires a past history of the site and if the user is not having any past history then the recommender system recommends the bestselling product or most popular product present in the market. Recommendation systems are effective tools for personalization, are always up-to-date, and gives a recommendation based on actual user behavior. Besides being useful in buying products it has a few disadvantages like it is difficult to set up and get running as they are database-driven. Sometimes recommendations are wrong which makes customers unsatisfied. Recommender system is used in different areas like recommendation for entertainment such as movies, songs etc., e-learning web site recommendation, newspaper recommendation and e-mail filters.
In this chapter, various recommendation techniques with their pros and cons and different evaluation metrices has been discussed.
Keywords: Recommendation, item-based, rating, artificial intelligence
1.1 Introduction
A recommender system is a sub-category of an information extraction system that helps to find the ranking or user preference for a particular item. Recommendation systems are dedicated software and methods that give ideas related to things that are used by different users [1, 2]. Many decisions can be made by considering recommendations like which product to purchase, type of music to listen, or what and where to read online news.
The things that are suggested by the system are known as "Item". A recommender system generally concentrates on a particular form of item like DVDs, or articles and thus its proposal, its graphical user interface (GUI), and the primary method used to make the suggestions are adapted to give beneficial and real recommendations for a particular form of item.
Consider an example of toy recommendation system that assists customers to select a toy to buy. The popular e-commerce web site i.e. Amazon.com also uses a recommendation system to identify the online store for every user [3]. As suggestions and choices are generally personalized, different users or user groups get different suggestions. In case of magazines and newspapers, non-personalized suggestions are produced, which are very easy to generate. Consider the example of selecting best ten books or CDs.
To make the personalized suggestions, ranked lists of items are produced. User's preferences and constrains are considered for generating the ranking to extract the most suitable products and services. For computing the most similar products and services, user's preferences are collected implicitly or explicitly by understanding the users' actions.
The fast development and diverse data existing on the web and existence of new e-business services like purchasing goods, comparing items, auction, etc. often stunned customers, leading them to make wrong choices. Thus, rather than giving benefit to customers, it starts decreasing the well-being. Actually, choice, with its insinuations of liberty, independence, and self-determination can become dangerous; generating a sense that independence may come to be observed as a kind of misery-inducing dictatorship [4].
These days, use of recommender systems has widely increased, indicated by the following facts:
- In high-rated internet sites, recommendation systems have a vital role like Yahoo, Amazon.com, Netflix, YouTube, TripAdvisor and IMDB. Now, RSs as a part of service have been provided to the subscriber by many media companies. For instance, Netflix, the online movie rental service, has paid a great price i.e. one million dollars as prize to the group that first successfully improved the accuracy of its recommendation system [3].
- ACM Recommender Systems (RecSys) has been established in 2007 dedicated for conferences and workshops.
1.2 Functions of Recommendation Systems
Recommender system offers suggestions to the user about a particular item that user wants to use. Now this definition can be refined by representing the different roles that a system can play. Recommender system plays different roles according to the user for example; a recommender system used by travel intermediary is usually used to increase the revenue like Expedia.com and Visitfinland.com while the customer's objective for using the systems is to find an appropriate hotel and interesting events/attractions when visiting a destination.
The following are different reasons to exploit RS technology by service providers:
- Increase the sale of product: The major objective of a commercial RS is to increase its sale, or in other words to sell those products also which can't be sold without recommendations. Recommendations are provided considering that suggested products and services meet the customer's requirements. Non-commercial recommendations are used for similar objectives. Consider an example of a content writer who wants to increase the number of news reader on his site. The goal of the service provider to use the recommender system is to increase the users that opts the products or services as compared to users surf the site.
- Selling variety of products: RS also help a user to find items that might be difficult to find without a particular reference. For example, the recommender system used in Netflix has the goal of renting maximum movies in the list, rather than the most popular movies. Making such recommendations could be hard without a recommender system because the service provider cannot take the risk of suggesting videos which do not meet the user's taste. In this way, the recommender system also suggests movies which are not even popular.
- User satisfaction. The recommender system helps in improving the experience of the person with the application or web site. It provides interesting, significant and, relevant recommendations as well as provides better human- computer interaction. The effective recommendations i.e. accurate as well as interactive user interface increases usage of the system and the chances that the suggestions will be acknowledged.
- User loyalty. A customer always prefers to use a web site or application which identifies its old users and treats him as a respected/valuable customer. It is a common feature of a recommender system as it computes recommendations/suggestions, considering the data attained from the user in earlier interactions such as his ratings of products. Therefore, the more the customer uses a particular site, the better his model becomes, i.e., output will be more customized to user's preferences.
- Better understand of user needs: The recommender system is acting as an active learner to user's preferences by collecting explicitly or predictions made by the system. The business holders may then re-use this information for improving the stock management or production of items.
1.3 Data and Knowledge Sources
Recommender systems are knowledge extraction systems that actively collect different types of information to make the suggestions. Facts are mostly related to things to be recommended and the consumers who will get such suggestions. Available data sources are very large and diverse, their use for making recommendations are largely depends upon the recommendation techniques to be used.
- Items: Products and services that a recommender system recommends are referred to as items. The recommendation of an item is considered positive if the suggested product is beneficial for the consumer. If the product is not meeting user requirements and the customer took a wrong decision while choosing it, then recommendation is negative.
- For example, a news recommender system designer must consider structure of news, the textual representation, and the time significance of any news. As while reading news, no monetary cost is associated but cognitive cost is there. If the system makes a positive recommendation, then cost of searching and reading news is dominated by the benefit of getting relevant and valuable knowledge. But if recommendation is negative, then the user's time is wasted which restricts the user to use the system again. In other areas, like mobile phones, or business investments, actual monetary cost is associated which becomes significant component to take into account while choosing the most suitable recommendation techniques.
- Examples of items having low difficulty and value are news, web articles, e-books, DVDs, and movies. Items having high complexity and value are laptops, LCDs, mobile phones, digital cameras, electrical appliances, PCs, etc. Insurance policies, travel plans, financial investments and jobs are considered as most complex items [10]. According to the basic recommendation approach, recommender systems use a variety of properties and characteristics of the products and services. For instance, in a movie recommendation, the genre like comedy, thriller, etc., as well as the actors, and...
