Huseyin Polat

Bio: Huseyin Polat is an academic researcher from Gazi University. The author has contributed to research in topics: Collaborative filtering & Recommender system. The author has an hindex of 26, co-authored 95 publications receiving 2201 citations. Previous affiliations of Huseyin Polat include Anadolu University & Syracuse University.

Privacy-preserving collaborative filtering using randomized perturbation techniques

Abstract: Collaborative filtering (CF) techniques are becoming increasingly popular with the evolution of the Internet. To conduct collaborative filtering, data from customers are needed. However, collecting high quality data from customers is not an easy task because many customers are so concerned about their privacy that they might decide to give false information. We propose a randomized perturbation (RP) technique to protect users' privacy while still producing accurate recommendations.

Shilling attacks against recommender systems: a comprehensive survey

Abstract: Online vendors employ collaborative filtering algorithms to provide recommendations to their customers so that they can increase their sales and profits. Although recommendation schemes are successful in e-commerce sites, they are vulnerable to shilling or profile injection attacks. On one hand, online shopping sites utilize collaborative filtering schemes to enhance their competitive edge over other companies. On the other hand, malicious users and/or competing vendors might decide to insert fake profiles into the user-item matrices in such a way so that they can affect the predicted ratings on behalf of their advantages. In the past decade, various studies have been conducted to scrutinize different shilling attacks strategies, profile injection attack types, shilling attack detection schemes, robust algorithms proposed to overcome such attacks, and evaluate them with respect to accuracy, cost/benefit, and overall performance. Due to their popularity and importance, we survey about shilling attacks in collaborative filtering algorithms. Giving an overall picture about various shilling attack types by introducing new classification attributes is imperative for further research. Explaining shilling attack detection schemes in detail and robust algorithms proposed so far might open a lead to develop new detection schemes and enhance such robust algorithms further, even propose new ones. Thus, we describe various attack types and introduce new dimensions for attack classification. Detailed description of the proposed detection and robust recommendation algorithms are given. Moreover, we briefly explain evaluation of the proposed schemes. We conclude the paper by discussing various open questions.

SVD-based collaborative filtering with privacy

Abstract: Collaborative filtering (CF) techniques are becoming increasingly popular with the evolution of the Internet. Such techniques recommend products to customers using similar users' preference data. The performance of CF systems degrades with increasing number of customers and products. To reduce the dimensionality of filtering databases and to improve the performance, Singular Value Decomposition (SVD) is applied for CF. Although filtering systems are widely used by E-commerce sites, they fail to protect users' privacy. Since many users might decide to give false information because of privacy concerns, collecting high quality data from customers is not an easy task. CF systems using these data might produce inaccurate recommendations. In this paper, we discuss SVD-based CF with privacy. To protect users' privacy while still providing recommendations with decent accuracy, we propose a randomized perturbation-based scheme.

Diagnosis of Chronic Kidney Disease Based on Support Vector Machine by Feature Selection Methods

Abstract: As Chronic Kidney Disease progresses slowly, early detection and effective treatment are the only cure to reduce the mortality rate. Machine learning techniques are gaining significance in medical diagnosis because of their classification ability with high accuracy rates. The accuracy of classification algorithms depend on the use of correct feature selection algorithms to reduce the dimension of datasets. In this study, Support Vector Machine classification algorithm was used to diagnose Chronic Kidney Disease. To diagnose the Chronic Kidney Disease, two essential types of feature selection methods namely, wrapper and filter approaches were chosen to reduce the dimension of Chronic Kidney Disease dataset. In wrapper approach, classifier subset evaluator with greedy stepwise search engine and wrapper subset evaluator with the Best First search engine were used. In filter approach, correlation feature selection subset evaluator with greedy stepwise search engine and filtered subset evaluator with the Best First search engine were used. The results showed that the Support Vector Machine classifier by using filtered subset evaluator with the Best First search engine feature selection method has higher accuracy rate (98.5%) in the diagnosis of Chronic Kidney Disease compared to other selected methods.

Detecting DDoS Attacks in Software-Defined Networks Through Feature Selection Methods and Machine Learning Models

Abstract: Software Defined Networking (SDN) offers several advantages such as manageability, scaling, and improved performance. However, SDN involves specific security problems, especially if its controller is defenseless against Distributed Denial of Service (DDoS) attacks. The process and communication capacity of the controller is overloaded when DDoS attacks occur against the SDN controller. Consequently, as a result of the unnecessary flow produced by the controller for the attack packets, the capacity of the switch flow table becomes full, leading the network performance to decline to a critical threshold. In this study, DDoS attacks in SDN were detected using machine learning-based models. First, specific features were obtained from SDN for the dataset in normal conditions and under DDoS attack traffic. Then, a new dataset was created using feature selection methods on the existing dataset. Feature selection methods were preferred to simplify the models, facilitate their interpretation, and provide a shorter training time. Both datasets, created with and without feature selection methods, were trained and tested with Support Vector Machine (SVM), Naive Bayes (NB), Artificial Neural Network (ANN), and K-Nearest Neighbors (KNN) classification models. The test results showed that the use of the wrapper feature selection with a KNN classifier achieved the highest accuracy rate (98.3%) in DDoS attack detection. The results suggest that machine learning and feature selection algorithms can achieve better results in the detection of DDoS attacks in SDN with promising reductions in processing loads and times.

The Self-Organizing Map

Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

Recommender systems survey

Abstract: Recommender systems have developed in parallel with the web. They were initially based on demographic, content-based and collaborative filtering. Currently, these systems are incorporating social information. In the future, they will use implicit, local and personal information from the Internet of things. This article provides an overview of recommender systems as well as collaborative filtering methods and algorithms; it also explains their evolution, provides an original classification for these systems, identifies areas of future implementation and develops certain areas selected for past, present or future importance.

Introduction to Recommender Systems Handbook

Abstract: Recommender Systems (RSs) are software tools and techniques providing suggestions for items to be of use to a user. In this introductory chapter we briefly discuss basic RS ideas and concepts. Our main goal is to delineate, in a coherent and structured way, the chapters included in this handbook and to help the reader navigate the extremely rich and detailed content that the handbook offers.

A distributed, architecture-centric approach to computing accurate recommendations from very large and sparse datasets

Abstract: The use of recommender systems is an emerging trend today, when user behavior information is abundant. There are many large datasets available for analysis because many businesses are interested in future user opinions. Sophisticated algorithms that predict such opinions can simplify decision-making, improve customer satisfaction, and increase sales. However, modern datasets contain millions of records, which represent only a small fraction of all possible data. Furthermore, much of the information in such sparse datasets may be considered irrelevant for making individual recommendations. As a result, there is a demand for a way to make personalized suggestions from large amounts of noisy data. Current recommender systems are usually all-in-one applications that provide one type of recommendation. Their inflexible architectures prevent detailed examination of recommendation accuracy and its causes. We introduce a novel architecture model that supports scalable, distributed suggestions from multiple independent nodes. Our model consists of two components, the input matrix generation algorithm and multiple platform-independent combination algorithms. A dedicated input generation component provides the necessary data for combination algorithms, reduces their size, and eliminates redundant data processing. Likewise, simple combination algorithms can produce recommendations from the same input, so we can more easily distinguish between the benefits of a particular combination algorithm and the quality of the data it receives. Such flexible architecture is more conducive for a comprehensive examination of our system. We believe that a user's future opinion may be inferred from a small amount of data, provided that this data is most relevant. We propose a novel algorithm that generates a more optimal recommender input. Unlike existing approaches, our method sorts the relevant data twice. Doing this is slower, but the quality of the resulting input is considerably better. Furthermore, the modular nature of our approach may improve its performance, especially in the cloud computing context. We implement and validate our proposed model via mathematical modeling, by appealing to statistical theories, and through extensive experiments, data analysis, and empirical studies. Our empirical study examines the effectiveness of accuracy improvement techniques for collaborative filtering recommender systems. We evaluate our proposed architecture model on the Netflix dataset, a popular (over 130,000 solutions), large (over 100,000,000 records), and extremely sparse (1.1%) collection of movie ratings. The results show that combination algorithm tuning has little effect on recommendation accuracy. However, all algorithms produce better results when supplied with a more relevant input. Our input generation algorithm is the reason for a considerable accuracy improvement.

Information privacy research: an interdisciplinary review

Abstract: To date, many important threads of information privacy research have developed, but these threads have not been woven together into a cohesive fabric. This paper provides an interdisciplinary review of privacy-related research in order to enable a more cohesive treatment. With a sample of 320 privacy articles and 128 books and book sections, we classify previous literature in two ways: (1) using an ethics-based nomenclature of normative, purely descriptive, and empirically descriptive, and (2) based on their level of analysis: individual, group, organizational, and societal. Based upon our analyses via these two classification approaches, we identify three major areas in which previous research contributions reside: the conceptualization of information privacy, the relationship between information privacy and other constructs, and the contextual nature of these relationships. As we consider these major areas, we draw three overarching conclusions. First, there are many theoretical developments in the body of normative and purely descriptive studies that have not been addressed in empirical research on privacy. Rigorous studies that either trace processes associated with, or test implied assertions from, these value-laden arguments could add great value. Second, some of the levels of analysis have received less attention in certain contexts than have others in the research to date. Future empirical studies-both positivist and interpretive--could profitably be targeted to these under-researched levels of analysis. Third, positivist empirical studies will add the greatest value if they focus on antecedents to privacy concerns and on actual outcomes. In that light, we recommend that researchers be alert to an overarching macro model that we term APCO (Antecedents → Privacy Concerns → Outcomes).