Context- Aware Recommender Systems (CARS)

Tailored services or information for mobile users became very crucial; due to the enormous amount of information and services that are available for mobile users during their various activities. Recommendation system can be merged with context awareness to provide tailored services, information, moreover learning resources for users, based on their current context and profile. Context Aware Recommendation Systems (CARSs) have various usages also many applications and services depend on it, CARSs nowadays become widely used in various domains. This paper presents a survey of CARSs overview, frameworks, techniques, algorithms, and applications. Moreover, the paper discusses the issues of CARSs in general and investigates the proposed solutions.

Context-aware rate enhancement (CARE) emerges as a promising solution to address the efficiency- and performance-related challenges of wireless networks by adapting the transmission rate based on contextual information. In this regard, machine learning (ML) algorithms can leverage context-awareness to provide personalized connectivity experiences by understanding user preferences, location information, and device capabilities. Hence, the main aim of this article is to explore the adoption of ML algorithms in wireless networks and the transformative impact they have on network management, performance optimization, and user experience. The motivating aspects of utilizing ML techniques in wireless networks are discussed, including efficiency, security, management, and quality of service (QoS) of wireless networks. The channel impulse response (CIR) predictor showed the efficiency of utilizing the recursive least square (RLS) algorithm yielding lower mean square error (MSE) than that of the outdated CIR predictors. Furthermore, incorporating contrast, noise, and illumination improvements into the local binary patterns (LBP) algorithm resulted in enhanced accuracy and boosted the overall quality of face detection/recognition performance compared with other traditional algorithms. Additionally, using natural language processing (NLP)-based data clustering algorithms can reduce the network traf ic while maintaining a high level of QoS for the user’s experience.

In the last years, we have witnessed the introduction of the Internet of Things (IoT) as an integral part of the Internet with billions of interconnected and addressable everyday objects. On one hand, these objects generate a massive volume of data that can be exploited to gain useful insights into our day-to-day needs. On the other hand, context-aware recommender systems (CARSs) are intelligent systems that assist users to make service consumption choices that satisfy their preferences based on their contextual situations. However, one of the key challenges facing the development and deployment of CARSs is the lack of functionality for providing dynamic and reliable context information required by the recommendation decision process. Thus, data obtained from IoT objects and other sources can be exploited to build CARSs that satisfy users’ preferences, improve quality of experience, and boost recommendation accuracy. This article describes various components of a conceptual IoT-base...

The unprecedented advancements in broadband and mobile networks, the proliferation and the incredible appeal of smart devices such as smartphones, and the recent emergence of cloud computing are poised to drive the next generation of ubiquitous media delivery and consumption. As more media services become available, mobile users will waste invaluable time, seeking relevant media items. Therefore, to deliver relevant media services, with rich experience to mobile users, media service providers must consider services that match user's contextual consumption choices. This paper proposes contextaware recommendation techniques to support the delivery of contextually relevant cloud-based media items to mobile users. The recommendation service works with a contextual user profile service, which relates user preferences to contexts in which such preferences are expressed, relying on a context recognition service, which identifies user's dynamic contextual situation from smartphone built-in sensors. Experimental evaluations, using real world user and online movie data, established that context-aware recommendation techniques are promising.

I also participated as a developer of Walkopedia® Infrastructure and the architecture defining but this work is not covered by this document. The explanation of Walkopedia® project is necessary to place the work presented on my master thesis, although Walkopedia® there isn't purpose of this document.

The improvements in the internet infrastructure and the increased affordability has led to an increase in the number of users on this platform. This has put a large impact on the services being offered on this platform especially on the e-commerce websites. These websites cater to the individual and the increased number of users has led to an increase in customer data. This data is highly valuable as it can allow for the effective prediction of customer behavior. Therefore, these predictions can allow for effective and accurate product recommendations based on the interests and the behavior of the customer. To achieve this approach, this research article analyzes a collection of related works based on the paradigm of product recommendation. After a thorough analysis, an improved product recommendation system is devised through the effective implementation of Natural Language Processing and machine learning algorithms. The proposed methodology performs preprocessing, Bag of Words, an...

With the rapid development of wireless communication and mobile internet, it is impossible to obtain high-quality recommendation just depending on traditional user-item binary relation. How to use multi-context to generate satisfying recommendation in such a complicated environment has been a hot pot in some fields like e-commerce, tourism, music and video. Context aware recommender system (CARS) import multi-context into recommender to generate recommendation with ubiquitousness and personalization. This paper presents an overview of the development status of CARS in recent years. We detail the definition of context, usage, process of CARS and evaluation. We also analyze some challengingresearch extension.

Providing recommendations in cold start situations is one of the most challenging problems for collaborative filtering based recommender systems (RSs). Although user social context information has largely contributed to the cold start problem, most of the RSs still suffer from the lack of initial social links for newcomers. For this study, we are going to address this issue using a proposed user similarity detection engine (USDE). Utilizing users’ personal smart devices enables the proposed USDE to automatically extract real-world social interactions between users. Moreover, the proposed USDE uses user clustering algorithm that includes contextual information for identifying similar users based on their profiles. The dynamically updated contextual information for the user profiles helps with user similarity clustering and provides more personalized recommendations. The proposed RS is evaluated using movie recommendations as a case study. The results show that the proposed RS can imp...

This work presents an extension of Thompson Sampling bandit policy for orchestrating the collection of base recommendation algorithms for e-commerce. We focus on the problem of item-to-item recommendations, for which multiple behavioral and attribute-based predictors are provided to an ensemble learner. In addition, we detail the construction of a personalized predictor based on k-Nearest Neighbors (kNN), with temporal decay capabilities and event weighting. We show how to adapt Thompson Sampling to realistic situations when neither action availability nor reward stationarity is guaranteed. Furthermore, we investigate the effects of priming the sampler with pre-set parameters of reward probability distributions by utilizing the product catalog and/or event history, when such information is available. We report our experimental results based on the analysis of three real-world e-commerce datasets.

The multi-armed bandit field is currently experiencing a renaissance, as novel problem settings and algorithms motivated by various practical applications are being introduced, building on top of the classical bandit problem. This article aims to provide a comprehensive review of top recent developments in multiple real-life applications of the multi-armed bandit. Specifically, we introduce a taxonomy of common MAB-based applications and summarize the state-of-the-art for each of those domains. Furthermore, we identify important current trends and provide new perspectives pertaining to the future of this burgeoning field.

Tailored services or information for mobile users became very crucial; due to the enormous amount of information and services that are available for mobile users during their various activities. Recommendation system can be merged with context awareness to provide tailored services, information, moreover learning resources for users, based on their current context and profile. Context Aware Recommendation Systems (CARSs) have various usages also many applications and services depend on it, CARSs nowadays become widely used in various domains. This paper presents a survey of CARSs overview, frameworks, techniques, algorithms, and applications. Moreover, the paper discusses the issues of CARSs in general and investigates the proposed solutions.

In today’s era, movie is considered to be important part of their lives. Movie will turn out to be an
activity for the people in which they are engaged frequently. Movie recommender system has developed into a
popular area for research. A superior movie recommendation method should be capable to involuntarily notice
preferences and make playlists accordingly. In this survey paper, we have given brief introduction of movie
recommendation system, recent work in movie recommendation system and conclusion.

Weather plays an important role in tourists' decision-making and, for instance, some places or activities must not be even suggested under dangerous weather conditions. In this paper we present a context-aware recommender system, named STS, that computes recommendations suited for the weather conditions at the recommended places of interest (POI) by exploiting a novel model-based context-aware recommendation technique. In a live user study we have compared the performance of the system with a variant that does not exploit weather data when generating recommendations. The results of our experiment have shown that the proposed approach obtains a higher perceived recommendation quality and choice satisfaction.

In this paper we give an overview of and outlook on research at the intersection of information retrieval (IR) and contextual bandit problems. A critical problem in information retrieval is online learning to rank, where a search engine strives to improve the quality of the ranked result lists it presents to users on the basis of those users' interactions with those result lists. Recently, researchers have started to model interactions between users and search engines as contextual bandit problems, and initial methods for learning in this setting have been devised. Our research focuses on two aspects: balancing exploration and exploitation and inferring preferences from implicit user interactions. This paper summarizes our recent work on online learning to rank for information retrieval and points out challenges that are characteristic of this application area.

In this paper we give an overview of and outlook on research at the intersection of information retrieval (IR) and contextual bandit problems. A critical problem in information retrieval is online learning to rank, where a search engine strives to improve the quality of the ranked result lists it presents to users on the basis of those users' interactions with those result lists. Recently, researchers have started to model interactions between users and search engines as contextual bandit problems, and initial methods for learning in this setting have been devised. Our research focuses on two aspects: balancing exploration and exploitation and inferring preferences from implicit user interactions. This paper summarizes our recent work on online learning to rank for information retrieval and points out challenges that are characteristic of this application area.

To follow the dynamicity of the user's content, researchers
have recently started to model interactions between users and the Context-
Aware Recommender Systems (CARS) as a bandit problem where the
system needs to deal with exploration and exploitation dilemma. In
this sense, we propose to study the freshness of the user's content in
CARS through the bandit problem. We introduce in this paper an algo-
rithm named Freshness-Aware Thompson Sampling (FA-TS) that man-
ages the recommendation of fresh document according to the user's risk
of the situation. The intensive evaluation and the detailed analysis of the
experimental results reveals several important discoveries in the explo-
ration/exploitation (exr/exp) behaviour

The vast amount of information generated and maintained everyday by information systems and their users leads to the increasingly important concern of overload information. In this context, traditional recommender systems provide relevant information to the users. Nevertheless, with the recent dissemination of mobile devices (smartphones and tablets), there is a gradual user migration to the use of pervasive computing environments.
The problem with the traditional recommendation approaches is that they do not utilize all available information for producing recommendations. More contextual parameters could be used in the recommendation process to result in more accurate recommendations. Context-Aware Recommender Systems (CARS) combine characteristics from context-aware systems and recommender systems in order to provide personalized recommendations to users in ubiquitous environments.
In this perspective where everything about the user is dynamic, his/her content and his/her environment, two main issues have to be addressed: i) How to consider content dynamicity? and ii) How to avoid disturbing the user in risky situations?. In response to these problems, we have developed a dynamic risk sensitive recommendation system called DRARS (Dynamic Risk-Aware Recommender System), which model the context-aware recommendation as a bandit problem. This system combines a content-based technique and a contextual bandit algorithm.
We have shown that DRARS improves the Upper Condence Bound (UCB) policy, the currently available best algorithm, by calculating the most optimal exploration value to maintain a trade-o between exploration and exploitation based on the risk level of the current user's situation. We conducted experiments in an industrial context with real data and real users and we have shown that taking into account the risk level of users' situations signicantly increased the performance of the recommender
systems.

Recently, researchers have started to model interactions between us-ers and search engines as an online learning ranking. Such systems obtain feed-back only on the few top-ranked documents results. To obtain feedbacks on other documents, the system has to explore the non-top-ranked documents that could lead to a better solution. However, the system also needs to ensure that the quality of result lists is high by exploiting what is already known. Clearly, this results in an exploration/exploitation dilemma. We introduce in this paper an algorithm that tackles this dilemma in Context-Based Information Retrieval (CBIR) area. It is based on dynamic exploration/exploitation and can adaptively balance the two aspects by deciding which user’s situation is most relevant for exploration or exploitation. Within a deliberately designed online framework we conduct evaluations with mobile users. The experimental results demon-strate that our algorithm outperforms surveyed algorithms.

Abstract The contextual bandit problem has been studied in the recommender system community, but without paying much attention to the contextual aspect of the recommendation. We introduce in this paper an algorithm that tackles this problem by modeling the Mobile Context-Aware Recommender Systems (MCRS) as a contextual bandit algorithm and it is based on dynamic exploration/exploitation.

Abstract: In this paper, we develop a dynamic exploration/exploitation (exr/exp) strategy for contextual recommender systems (CRS). Specifically, our methods can adaptively balance the two aspects of exr/exp by automatically learning the optimal tradeoff. This consists of optimizing a utility function represented by a linearized form of the probability distributions of the rewards of the clicked and the non-clicked documents already recommended.

Most existing approaches in Mobile Context-Aware Recommender Systems focus on recommending relevant items to users taking into account contextual information, such as time, location, or social aspects. However, none of them has considered the problem of user's content evolution. We introduce in this paper an algorithm that tackles this dynamicity. It is based on dynamic exploration/exploitation and can adaptively balance the two aspects by deciding which user's situation is most relevant for exploration or exploitation. Within a deliberately designed offline simulation framework we conduct evaluations with real online event log data. The experimental results demonstrate that our algorithm outperforms surveyed algorithms.

The wide development of mobile applications provides a considera-ble amount of data of all types. In this sense, Mobile Context-aware Recom-mender Systems (MCRS) suggest the user suitable information depending on her/his situation and interests. Our work consists in applying machine learning techniques and reasoning process in order to adapt dynamically the MCRS to the evolution of the user’s interest. To achieve this goal, we propose to combine bandit algorithm and case-based reasoning in order to define a contextual rec-ommendation process based on different context dimensions (social, temporal and location). This paper describes our ongoing work on the implementation of a MCRS based on a hybrid-ε-greedy algorithm. It also presents preliminary re-sults by comparing the hybrid-ε-greedy and the standard ε-greedy algorithm.

The wide development of mobile applications provides a considerable amount of data of all types (images, texts, sounds, videos, etc.). In this sense, Mobile Context-aware Recommender Systems (MCRS) suggest the user suitable information depending on her/his situation and interests. Two key questions have to be considered 1) how to recommend the user information that follows his/her interests evolution? 2) how to model the user’s situation and its related interests? To the best of our knowledge, no existing work proposing a MCRS tries to answer both questions as we do. This paper describes an ongoing work on the implementation of a MCRS based on the hybrid-ε-greedy algorithm we propose, which combines the standard ε-greedy algorithm and both content-based filtering and case-based reasoning techniques.