Nikolaos Polatidis

A multi-level collaborative filtering method that improves recommendations

We propose a recommendation method that improves collaborative filtering.We divide the Pearson Correlation Similarity (PCC) in multiple levels.The proposed method has been tested on five real datasets.A comparison to alternative methods is provided in order to show its effectiveness. Collaborative filtering is one of the most used approaches for providing recommendations in various online environments. Even though collaborative recommendation methods have been widely utilized due to their simplicity and ease of use, accuracy is still an issue. In this paper we propose a multi-level recommendation method with its main purpose being to assist users in decision making by providing recommendations of better quality. The proposed method can be applied in different online domains that use collaborative recommender systems, thus improving the overall user experience. The efficiency of the proposed method is shown by providing an extensive experimental evaluation using five real datasets and with comparisons to alternatives.

A dynamic multi-level collaborative filtering method for improved recommendations

One of the most used approaches for providing recommendations in various online environments such as e-commerce is collaborative filtering. Although, this is a simple method for recommending items or services, accuracy and quality problems still exist. Thus, we propose a dynamic multi-level collaborative filtering method that improves the quality of the recommendations. The proposed method is based on positive and negative adjustments and can be used in different domains that utilize collaborative filtering to increase the quality of the user experience. Furthermore, the effectiveness of the proposed method is shown by providing an extensive experimental evaluation based on three real datasets and by comparisons to alternative methods. We propose a method that improves collaborative filtering recommendations.It may use either a static or a dynamic multi-level approach.It is based on positive and negative adjustments of the users similarity values.Both approaches have been experimentally evaluated using three real datasets.Our approaches produce results of better quality when compared to alternatives.

Privacy-preserving collaborative recommendations based on random perturbations

We propose a solution to the privacy problem found in collaborative filtering.Our proposed method is based on multiple levels.We have evaluated our method using five real datasets and well known metrics. Collaborative recommender systems offer a solution to the information overload problem found in online environments such as e-commerce. The use of collaborative filtering, the most widely used recommendation method, gives rise to potential privacy issues. In addition, the user ratings utilized in collaborative filtering systems to recommend products or services must be protected. The purpose of this research is to provide a solution to the privacy concerns of collaborative filtering users, while maintaining high accuracy of recommendations. This paper proposes a multi-level privacy-preserving method for collaborative filtering systems by perturbing each rating before it is submitted to the server. The perturbation method is based on multiple levels and different ranges of random values for each level. Before the submission of each rating, the privacy level and the perturbation range are selected randomly from a fixed range of privacy levels. The proposed privacy method has been experimentally evaluated with the results showing that with a small decrease of utility, user privacy can be protected, while the proposed approach offers practical and effective results.

Mobile recommender systems: An overview of technologies and challenges

The use of mobile devices in combination with the rapid growth of the internet has generated an information overload problem. Recommender systems is a necessity to decide which of the data are relevant to the user. However in mobile devices there are different factors who are crucial to information retrieval, such as the location, the screen size and the processor speed. This paper gives an overview of the technologies related to mobile recommender systems and a more detailed description of the challenged faced.

A ubiquitous recommender system based on collaborative filtering and social networking data

The use of mobile devices and the rapid growth of the internet and networking infrastructure has brought the necessity of using ubiquitous recommender systems. However, in mobile devices there are different factors that need to be considered in order to get more useful recommendations and increase the quality of the user experience. This paper gives an overview of the factors related to the quality and proposes a new hybrid recommendation model. The proposed model is based on collaborative filtering and social rating network data. Furthermore, it includes an approach to protect user privacy when context parameters are used, by transferring a subset of the users and ratings in the mobile device and applying the algorithm and context parameters locally. In addition, we recommend the use of classical user-based collaborative filtering, enhanced by the trust network, which is a method that performs better in terms of accuracy when compared with user-based collaborative filtering and trust-aware collaborative filtering. Our approach has been experimentally evaluated and is shown that is both practical and effective.

Factors Influencing the Quality of the User Experience in Ubiquitous Recommender Systems

The use of mobile devices and the rapid growth of the internet and networking infrastructure has brought the necessity of using Ubiquitous recommender systems. However in mobile devices there are different factors that need to be considered in order to get more useful recommendations and increase the quality of the user experience. This paper gives an overview of the factors related to the quality and proposes a new hybrid recommendation model.

Recommender Systems: The Importance of Personalization in E-Business Environments

Due to the rapid growth of the internet in conjunction with the information overload problem the use of recommender systems has started to become necessary for both e-businesses and customers. However there are other factors such as privacy and trust that make customers suspicious. This paper gives an overview of recommendation systems, the benefits that both the business and the customers have and an explanation of the challenges, which if faced can make the personalization process better for both parties. Moreover an outline of current studies is given along with an overview of Amazon’s recommendations in order to clarify that the use of recommender systems is beneficial for an e-business in many ways and also for a valuable customer of such business. Recommender Systems: The Importance of Personalization in E-Business Environments

Privacy-preserving recommendations in context-aware mobile environments

Purpose This paper aims to address privacy concerns that arise from the use of mobile recommender systems when processing contextual information relating to the user. Mobile recommender systems aim to solve the information overload problem by recommending products or services to users of Web services on mobile devices, such as smartphones or tablets, at any given point in time and in any possible location. They use recommendation methods, such as collaborative filtering or content-based filtering and use a considerable amount of contextual information to provide relevant recommendations. However, because of privacy concerns, users are not willing to provide the required personal information that would allow their views to be recorded and make these systems usable. Design/methodology/approach This work is focused on user privacy by providing a method for context privacy-preservation and privacy protection at user interface level. Thus, a set of algorithms that are part of the method has been designed with privacy protection in mind, which is done by using realistic dummy parameter creation. To demonstrate the applicability of the method, a relevant context-aware data set has been used to run performance and usability tests. Findings The proposed method has been experimentally evaluated using performance and usability evaluation tests and is shown that with a small decrease in terms of performance, user privacy can be protected. Originality/value This is a novel research paper that proposed a method for protecting the privacy of mobile recommender systems users when context parameters are used.

Cyber-attack path discovery in a dynamic supply chain maritime risk management system

Maritime port infrastructures rely on the use of information systems for collaboration, while a vital part of collaborating is to provide protection to these systems. Attack graph analysis and risk assessment provide information that can be used to protect the assets of a network from cyber-attacks. Furthermore, attack graphs provide functionality that can be used to identify vulnerabilities in a network and how these can be exploited by potential attackers. Existing attack graph generation methods are inadequate in satisfying certain requirements necessary in a dynamic supply chain risk management environment, since they do not consider variables that assist in exploring specific network parts that satisfy certain criteria, such as the entry and target points, the propagation length and the location and capability of the potential attacker. In this paper, we present a cyber-attack path discovery method that is used as a component of a maritime risk management system. The method uses constraints and Depth-first search to effectively generate attack graphs that the administrator is interested in. To support our method and to show its effectiveness we have evaluated it using real data from a maritime supply chain.

A Method for Privacy-Preserving Context-Aware Mobile Recommendations

Mobile recommender systems aim to solve the information overload problem found by recommending products or services to users of mobile smartphones or tables at any given point in time and in any possible location. Mobile recommender systems are designed for the specific goal of mobile recommendations, such as mobile commerce or tourism and are ported to a mobile device for this purpose. They utilize a specific recommendation method, like collaborative filtering or content-based filtering and use a considerable amount of contextual information in order to provide more personalized recommendations. However due to privacy concerns users are not willing to provide the required personal information to make these systems usable. In response to the privacy concerns of users we present a method of privacy preserving context-aware mobile recommendations and show that it is both practical and effective.