Recommender system, Collaborative filtering

Recommendation becomes a mainstream feature in nowadays e-commerce because of its significant contributions in promoting revenue and customer satisfaction. Given hundreds of millions of user activity logs and product items, accurate and efficient recommendation is a challenging computational task. This paper introduces a new soft hierarchical clustering algorithm-Fuzzy Hierarchical Co-clustering (FHCC) algorithm, and applies this algorithm to detect user-product joint groups from users' behavior data for collaborative filtering recommendation. Via FHCC, complex relations among different data sources can be analyzed and understood comprehensively. Besides, FHCC is able to adapt to different types of applications according to the accessibility of data sources by carefully adjust the weights of different data sources. Experimental evaluations are performed on a benchmark rating dataset to extract user-product co-clusters. The results show that our proposed approach provide more meaningful recommendation results, and outperforms existing item-based and user-based collaborative filtering recommendations in terms of accuracy and ranked position.

Many recommendation algorithms suuer from popularity bias in their output: popular items are recommended frequently and less popular ones rarely, if at all. However, less popular, long-tail items are precisely those that are ooen desirable recommendations. In this paper, we introduce a exible regularization-based framework to enhance the long-tail coverage of recommendation lists in a learning-to-rank algorithm. We show that regularization provides a tunable mechanism for controlling the trade-oo between accuracy and coverage. Moreover, the experimental results using two data sets show that it is possible to improve coverage of long tail items without substantial loss of ranking performance.

Recommender system is a helpful tool for helping the user in cutting the time needs to find personalized products, documents, friends, places and services. In addition, the recommender system handles the century web problem: information overload. In the same time, many environments or technologies (i.e. cloud, mobile, social network) become popular today and facing the problem of large amount of information. Therefore, the researchers recognize that the recommender system is a suitable solution to this problem in those environments. This paper, reviews the recent research papers that were applied the recommender system in mobile, social network, or cloud environment. We classify these recommender systems into four groups (i.e. mobile recommender system, social recommender system, cloud recommender system and traditional (PC) recommender system) depending on technology or environment that the RS is applied in. This survey presents some compression, advantages and challenges of these types of recommender systems. Also, it will directly support researchers and professionals in their understanding of those types of recommender systems.

The virtual world overflowing with the digital items which make the searching, choosing and shopping hard tasks for users. The recommender system is a smart filtering tool for generate a list of potential favorite items for the user to reduce the time needed by user to
choose among a huge number of choices in websites and facilitate the process.
In that context, this thesis presents a novel technique that combines the ideas of item-based semantic similarity, n-criteria and multi-filtering criteria with the genetic-based recommender system. The genetic algorithm is utilized in order to predict the best list of items to the active user. Consequently, each individual in the population represents a candidate recommendation list. Each list subjects to three tests to measure the quality of it.
The proposed system alleviates the effect of the sparsity and cold start problems and makes the recommender system capable of generating recommendation without the need of using a similarity metric or requires any additional information provided by the hybrid system. Furthermore and due to the fact that there are many environments facing the information overload problem, the author presents a new classification of the recommender system based on the environment that is applied in.
The proposed system is evaluated against the state-of-the-art genetic-based recommender system and the traditional techniques that used in collaborative filtering recommender system. The results obtained show that the proposed method outperforms these algorithms in prediction accuracy by 24.3%, recommendation quality by 33.5% and performance (CPU time) by 45.4%. Moreover, the results showed that 69.5% of the recommended items are truly favorite items to the active user. The remainders 30.5% of the recommended items are potential favorite items.

The virtual world overflowing with the digital items which make the searching, choosing
and shopping hard tasks for users. The recommender system is a smart filtering tool for
generate a list of potential favorite items for the user to reduce the time needed by user to
choose among a huge number of choices in websites and facilitate the process.
In that context, this thesis presents a novel technique that combines the ideas of itembased
semantic similarity, n-criteria and multi-filtering criteria with the genetic-based
recommender system. The genetic algorithm is utilized in order to predict the best list of
items to the active user. Consequently, each individual in the population represents a
candidate recommendation list. Each list subjects to three tests to measure the quality of it.
The proposed system alleviates the effect of the sparsity and cold start problems and makes
the recommender system capable of generating recommendation without the need of using
a similarity metric or requires any additional information provided by the hybrid system.
Furthermore and due to the fact that there are many environments facing the
information overload problem, the author presents a new classification of the
recommender system based on the environment that is applied in.
The proposed system is evaluated against the state-of-the-art genetic-based
recommender system and the traditional techniques that used in collaborative filtering
recommender system. The results obtained show that the proposed method outperforms
these algorithms in prediction accuracy by 24.3%, recommendation quality by 33.5% and
performance (CPU time) by 45.4%. Moreover, the results showed that 69.5% of the
recommended items are truly favorite items to the active user. The remainders 30.5% of the
recommended items are potential favorite items.

( Alternatif Link download Buku Analisis Big Data: http://bit.ly/2x8ta9S )

Alhamdulillahhi robbil alamin, puji syukur kehadirat Allah SWT atas segala rahmat dan karunia-Nya dengan terselesaikannya penulisan buku ini dengan judul “Analisis Big Data”. Buku ini merupakan uraian untuk memudahkan pemahaman konsep, tingkat dasar sampai lanjut dalam sistem cerdas dan penerapannya melalui pemanfaatan teknologi Big Data, dengan mengedepankan keterampilan dalam pembuatan dan hasil implementasi dengan berbagai kombinasi algoritma berbasis sistem cerdas maupun dengan perpaduan berbagai macam tools untuk membangun ekosistem analisis Big Data yang powerfull. Konsep sederhana Analisis Big Data mencakup Volume, Velocity, dan Variety (3V), dan pengembangannya ada yang menyebut (7V) termasuk Volume, Velocity, Variety, Variability, Veracity, Value dan Visualization, atau 10V bahkan lebih dari itu, tetapi sebaiknya tidak membatasi pemahaman Big Data ini hanya dengan sedikit banyaknya istilah dari huruf V yang digunakan :). Kemudian dengan adanya ekosistem tersebut, jika dibutuhkan analisis sederhana maupun yang lebih kompleks, maka harapannya tidak akan ada kendala dari besarnya data yang diolah. Adanya kemajuan teknologi dalam hal penyimpanan, pengolahan, dan analisis Big Data meliputi (a) penurunan secara cepat terhadap biaya penyimpanan data dalam beberapa tahun terakhir; (b) fleksibilitas dan efektivitas biaya pada pusat data dan komputasi awan untuk perhitungan dengan konsep elastisitas dan penyimpanannya; serta (c) pengembangan kerangka kerja baru seperti Hadoop ecosystem (salah satu peluang bisnis yang besar untuk developer untuk saat ini dan ke depannya dalam rangka membangun ekosistem analisis Big Data yang sangat powerfull sekelas Cloudera, Hortonworks, etc), yang memungkinkan pengguna untuk mengambil manfaat dari sistem komputasi terdistribusi, misal untuk menyimpan sejumlah data yang besar melalui pemrosesan parallel, dukungan database NoSQL, dan komputasi berbasis streaming. Sehingga kemajuan teknologi ini telah menciptakan beberapa perbedaan yang sangat signifikan, misal dalam hal kecepatan maupun ketepatan dari hasil yang didapatkan antara analisis tradisional dengan tools yang bukan dengan konsep Big Data versus analisis modern untuk saat ini dan masa depan dengan membangun ekosistem Big Data yang sangat powerfull.
Penulis mengucapkan terimakasih yang sebesar-besarnya kepada kedua orang tua penulis, spesial kepada Istriku tercinta “Alfun Lailatul Musabbikha”, bapak ibu mertua, dik Wiwik, dik Ganda, kak Mat, kak Deri, Bude Gi, Pakde Dul, Bude Gani, Pak Abu, mbak Nik, dik Andre, Mbak As, Mbak Lia, Mas Mualif, Mbak Lis, Pakde Naji, Bulik Yul, Pakde Tasrun, Pakde Zen, Pakde Zud, Paklik Fiq, mas Bowo dan semua sanak saudaraku yang tak bisa kusebutkan seluruhnya, serta beberapa pihak yang telah membantu penyelesaian buku ini:
1. Para penulis artikel Analisis Big Data di forum, web, blog dan buku yang menjadi referensi buku ini untuk memberikan masukan yang sangat berharga sekali untuk perbaikan dan penyelesaian buku ini.
2. Mbak Efi Riyandani, yang telah banyak membantu penulisan buku, dan mahasiswa-mahasiswa terbaik saya semester Ganjil 2016/2017, yaitu: Maryamah, Moh. Fadel Asikin, Daisy Kurniawaty, Selly Kurnia Sari, Nanda Agung Putra, Ardisa Tamara Putri, Dhimas Anjar Prabowo, Listiya Surtiningsih, Raissa Arniantya, Brillian Aristyo Rahadian, Diva Kurnianingtyas, Dyan Putri Mahardika, Tusty Nadia Maghfira.
3. Mahasiswa-mahasiswa terbaik saya semester Ganjil 2017/2018, yaitu: Yessica Inggir F., Kholifaul K., Ni Made Gita D. P., Ema Agasta, Retiana Fadma P. Sinaga, Fachrul Rozy Saputra Rangkuti, Yunita Dwi Alfiyanti, Dyah Ayu Wahyuning Dewi, Annisaa Amalia Safitri, Sarah Aditya Darmawan, Danastri Ramya Mehaninda, Eka Novita Shandra, Fakharuddin Farid Irfani, Rio Cahyo Anggono, Robih Dini, Yulia Kurniawati, Novirra Dwi Asri, Muhammad Vidi Mycharoka, Vania Nuraini Latifah, Olivia Bonita, Eka Miyahil Uyun, Cusen Mosabeth, Evilia Nur Harsanti, Ivarianti Sihaloho.

Semoga kontribusi kalian menjadi ilmu yang barokah dan bermanfaat. Aamiin. :). Tidak ada gading yang tak retak. Maka penulis memohon kritik dan saran untuk perbaikan dan penyempurnaan buku ini. In Syaa Allah pada edisi berikutnya, kami akan memberikan manualisasi Map Reduce, Spark, etc. dari setiap algoritma pada setiap contoh kasusnya. Selamat membaca buku ini dan semoga bermanfaat.

Malang, 19 Juli 2016-24 Mei 2018

Penulis

With the increase of volume, velocity, and variety of big data, the traditional collaborative filtering recommendation algorithm, which recommends the items based on the ratings from those like-minded users, becomes more and more inefficient. In this paper, two varieties of algorithms for col-laborative filtering recommendation system are proposed. The first one uses the improved k-means clustering technique while the second one uses the improved k-means clustering technique coupled with Principal Component Analysis as a dimensionality reduction method to enhance the recommendation accuracy for big data. The experimental results show that the proposed algorithms have better recommendation performance than the traditional collaborative filtering recommendation algorithm.

Recommender systems can be implemented in several fields beginning E-commerce to set- up protection in the structure of personalized services. They offer assistance to mutually consumers and the manufacturers, through suggested matter to the consumers, which cannot exist demand until the recommendations given.User's input their preferred hotel features. (e.g. Pool,Gym, Restaurant, etc..) after the user's log-in, the content-based filtering SVM algorithm analyzes the hotel features and generates recommendations of what classes of the hotel it features. Classification through the procedure of Support Vector Machines (SVMs) is being suggested by putting away of user’s preferences in several activities and its equivalent characteristics therefore vectors are completed. The collaborative filtering generates filtered hotels constructed on the user's earlier involvement (Review, Rooms, Evaluations, and Prices) in some relationships with statistical method.Among the various classifications of algorithms are K-nearest neighbor, Naïve Bayes, Random Forest, and Support Vector Machine.The SVM was chosen as a previous research from Duvvur that shows more accurate than other models

—Recommender systems aim to help web users to find only close information to their preferences rather than searching through undifferentiated mass of information. Currently, col-laborative filtering is probably the most known and commonly used recommendation approach in recommender systems. In this paper, we present a new genetic algorithms-based recommender system, SimGen, that computes the similarity values between users without using any of the well-known similarity metric calculation algorithms like Pearson correlation and vector cosine-based similarity. The results obtained present 46% and 38% improvements in prediction quality and performance, respectively when compared with other techniques.

Web applications use recommendation techniques that are based on users' preferences for items to
recommend interesting items to the active user. Users' preferences can be their activities on these items such as:
rate, view, etc. Collaborative filtering (CF) is the most successfully used recommendation system recently; it is
based on the similarities between users and the similarities between items. However, users' opinions and items'
popularities vary with time. These variations decrease the recommendation accuracy. Many researchers study
ways of using Morkov model in recommendation systems; however, they do not consider the time factor in their
techniques. In this paper, we propose a new recommendation system that is based on Morkov model, and it
considers the time factor. We compare our new technique with the conventional CF recommendation system for
the evaluation. We conduct the experiments using MovieLens dataset. The evaluation is done by using precisionrecall,
and mean absolute error. The result illustrates that our new recommendation system outperforms the
conventional CF recommendation system.

This article reports on a modification of the user-kNN algorithm that measures the similarity between users based on the similarity of text reviews, instead of ratings. We investigate the performance of text semantic similarity measures and we evaluate our text-based user-kNN approach by comparing it to a range of ratings-based approaches in a ratings prediction task. We do so by using datasets from two different domains: movies from RottenTomatoes and Audio CDs from Amazon Products. Our results show that the text-based user-kNN algorithm performs significantly better than the ratings-based approaches in terms of accuracy measured using RMSE.

In the last twelve years, the number of web user increases, so intensely leading to intense advancement in web services which leads to enlargement the usage data at higher rates. The purpose of a recommender System is to generate meaningful recommendations to a collection of users for items or products that might interest them. Recommender systems differ in the way they analyze these data sources to develop notions of congeniality between users and items which can be used to identify well-matched pairs. The recommender system technology intentions to help users in finding items that match their personal interests. It has a successful usage in e-commerce applications to deal with problems related to information overload proficiently. In this paper, we will extensively present a survey of six existing recommendation system. The Collaborative Filtering systems analyze historical interactions alone, while Content-Based Filtering systems are based on profile attributes, Hybrid Techniques attempt to combine both of these designs, Demographic Based Recommender systems aim to categorize the user based on personal attributes and make recommendations based on demographic classes, while Knowledge-Based Recommendation attempts to suggest objects based on inferences about a user's needs and preferences, and Utility-Based Recommender systems make recommendations based on the computation of the utility of each item for the user. In this paper, we have recognized 60 research papers on recommender systems, which were published between 1971 and 2014. Finally, few research papers had an influence on research paper recommender systems in practice. We also recognized a lack of authority and long term research interest in the field, 78% of the authors published no more than one paper on research paper recommender systems, and there was miniature cooperation among different co-author groups.

The Web is currently characterised by user contribution. As a result, content is generated in an uncontrolled way leading to the so-called “info r mation overload”. The role of information filtering techniques and recommender systems is to give a solution to this problem by taking into account user preferences, and/or other context of information to present the content. Furthermore, word-of-mouth and trust plays a key role in the decision-making process of a person, while ratings, comments, opinions and tags are increasingly gaining popularity in social networks. The aim of this paper is to study the current approaches of trust-aware recommender systems with a focus on graph based models and to identify possible gaps for providing insights and directions for future researches. In the beginning there is an introduction with presentation of traditional recommendation approaches along with their limitations. Then there is a review of trust definitions and properties. It follows a review of current trust-aware approaches which are classified in five major categories according the technique they use. In the last section there is a focus on graph models of trust-aware recommender systems which are compared according four categorisation criteria. Finally the study identifies the gaps in the current literature of graph based models and proposes areas for future research.

In this paper, we present a recommendation system named as RSF for farmers, which can recommend farmers most suitable crops to produce in different areas. The system first detects a user's location and works with different agro-ecological and agro-climatic data in upazila level to calculate similarity between upazilas using pearson co-relation similarity algorithm. Then it selects top-n similar upazilas. Finally, utilizing the seasonal information and crop production rates of each crop of the similar upazilas, it recommends top-k crops to a user of a upazila. The system has been evaluated with real data and we have found a reasonable and satisfactory accuracy. The system can help farmers in producing appropriate crops. As a result, they can increase their lifestyle and can contribute more to the society. We provided the system layout both in Bangla and English so that the farmers as well as the people who works with farmers can get help easily from this.

—Information filtering and recommender systems exploit various techniques to deal with the information overload problem. One popular technique for making recommendations is based on trust statements between users in a social network. Yet explicit trust statements are usually very sparse leading to the need for expanding the trust networks by inferring new trust relationships. This study proposes a novel model to infer new trusted neighbors and combines it with existing methods to achieve a fully expanded trust network. Experimental results demonstrate that the proposed method outperforms the existing methods.

ABSTRAK Transaksi perdagangan merupakan salah satu kegiatan yang sering dijumpai pada kehidupan sehari-hari. Pesatnya perkembangan teknologi informasi sekarang ini, berdampak transaksi perdagangan tidak hanya menggunakan cara konvensional tetapi telah memanfaatkan teknologi informasi. Untuk itu, diperlukan sistem yang dapat memberikan rekomendasi yang dianggap sesuai dengan keinginan pelanggan. Makalah ini menyajikan pengembangan sistem rekomendasi pada toko buku online menggunakan item collaborative filtering dengan metode waterfall. Metode rekomendasi yang digunakan didasarkan atas adanya kesamaan antara pemberian rating terhadap suatu produk dengan produk yang dibeli. Sistem diimplementasikan pada toko buku Social Agency Baru, Yogyakarta. Sistem ini diharapkan dapat memberikan kemudahan bagi pelanggan dalam memilih buku yang dianggap sesuai dengan pelanggan tersebut. Kata kunci: Item Collaborative Filtering, toko buku online, PHP, dan WML

With the advent and explosive growth of the Web over the past decade, recommender systems have become at the heart of the business strategies of e-commerce and Internet-based companies such as Google, YouTube, Facebook, Netflix, LinkedIn, Amazon, etc. Hence, the collaborative filtering recommendation algorithms are highly valuable and play a vital role at the success of such businesses in reaching out to new users and promoting their services and products. With the aim of improving the recommendation performance of such an algorithm, this paper proposes a new collaborative filtering recommendation algorithm based on dimensionality reduction and clustering techniques. The k-means algorithm and Singular Value Decomposition (SVD) are both used to cluster similar users and reduce the dimensionality. It proposes and evaluates an effective two stage recommender system that can generate accurate and highly efficient recommendations. The experimental results show that this new method significantly improves the performance of the recommendation systems .

This paper focuses on recommender systems based on item-item collaborative filtering (CF). Although research on item-based methods is not new, current literature does not provide any reliable insight on how to estimate confidence of recommendations. The goal of this paper is to fill this gap, by investigating the conditions under which item-based recommendations will succeed or fail for a specific user. We formalize the item-based CF problem as an eigenvalue problem , where estimated ratings are equivalent to the true (unknown) ratings multiplied by a user-specific eigenvalue of the similarity matrix. We show that the magnitude of the eigenvalue related to a user is proportional to the accuracy of recommendations for that user. We define a confidence parameter called the eigenvalue confidence index, analogous to the eigenvalue of the similarity matrix, but simpler to be computed. We also show how to extend the eigen-value confidence index to matrix-factorization algorithms. A comprehensive set of experiments on five datasets show that the eigenvalue confidence index is effective in predicting, for each user, the quality of recommendations. On average, our confidence index is 3 times more correlated with MAP with respect to previous confidence estimates.

Web-based application for rents baby and child equipment is an e-commerce that implements the concept of a marketplace and designed to make it easier for owners of items and customers to do the activities of leasing. The concept of marketplace serves to bring the owners of items and customers into a platform where they can do rental activities in accordance with their needs, also safer and more efficient in transactions. Many choices of items for rent sometimes make customers have trouble when choosing items that suit their needs and taste. Recommender system that will be applied in these apps is used for give product recommendations to all customers. One of methods that used for build recommender system is item-based collaborative filtering. Implementation of recommender system in this case this apps use item-based collaborative filtering method has resulted Top-5 Recommendation Product which features qualified recommendation items for customers which can be viewed based on the rating given by previous consumers.

O estudo de sistemas de recomendação é relativamente novo, razão inicial para a motivação desta dissertação. Ao estudar melhor o mercado de varejo de moda no Brasil, percebe-se o vasto espaço para a aplicação dessas soluções. Basta correlacionar as peças e os clientes para que isso fique ainda mais evidente. Em contrapartida, o estudo faz perceber a falta de aplicações desse tipo de sistema em ambientes off-line. Este trabalho parte da revisão teórica do tema em questão e propõe a aplicação de soluções de recomendação nas redes de varejo de moda, como forma de melhor aproveitar os investimentos em marketing e aperfeiçoar a reposição dos estoques das lojas.

One form of complexity in intelligent environments arises from their heterogeneous nature. The growing variety of environments and countless stereotypes of users operating Intelligent Environments will, theoretically, increase the complexity and resources needed to utilise them. However we argue that utilizing Crowd Intelligence techniques in Intelligent Environments offer several advantages for dealing with these complexities. A novel architecture called a Crowd Based Heterogeneous Ambient Environment Framework (CHAMBER) is introduced, which proposes the use of hierarchical clustering to discover similarities between the infrastructures of individual Intelligent Environments, which are then offered for use by other users wishing to construct their own intelligent environments.

In the “real world” today, we are constantly exposed to information we may not
necessarily be interested in. In the “virtual world” however, we can make
Intelligent agents work for us and in that way receive the information we
specifcally want to see. So far, the “virtual world” has expanded to great
dimensions and has already generated impressive quantities of social network
sites. The explosive growth of the Web has increased the demand for intelligent
semantic-driven personalized recommendation systems which are able to
“think” and “reason” on their own. Through the presence of user personalized
profles on the Web, we have come one step closer to creating the world which
provides us with an experience which is tailored to the user...

A course recommender system has a great importance in expecting the selection of courses by students in an university, especially for new students who can't easily select the proper elective courses offered for a specific semester. The computer science department in Ajloun University College at Balqa Applied University (BAU) will be taken as a case study. In this paper, an efficient cluster based rule mining algorithm will be used on a course database to describe a courses recommendation system that assist students to choose elective courses based on students already studied these courses or some of them.

Collaborative Filtering is generally used as a recommender system. There is enormous growth in the amount of data in web. These recommender systems help users to select products on the web, which is the most suitable for them. Collaborative filtering-systems collect user's previous information about an item such as movies, music, ideas, and so on. For recommending the best item, there are many algorithms, which are based on different approaches. The most known algorithms are User-based and Item-based algorithms. Experiments show that Item-based algorithms give better results than User-based algorithms. The aim of this paper isto compare User-based and Item-based Collaborative Filtering Algorithms with many different similarity indexes with their accuracy and performance. We provide an approach to determine the best algorithm, which give the most accurate recommendation by using statistical accuracy metrics. The results are compared the User-based and Item-based algorithms with movie recommendation data set.

Recommender systems are widely used in businesses, and the growth of e-commerce has seen an explosion of such systems. The Netflix Prize seeks to substantially improve the accuracy of user movie rating prediction. The data set is huge, and consists of only three explicit variables. The challenge has been ongoing for almost three years, and most of the leading teams have used multiple machine-learning models to improve their predictions. While such prediction improvement is commendable, it provides little insight into the process of recommendation, and does not create actionable intelligence for decision makers to plan for future business growth. Our model incorporates parameter optimization, followed by segment generation, to improve on the prediction. Our method can be intuitively explained in terms of the impact of a movie’s rating by other users, as well as a given user’s preferences. Using these methods, we show improvement in the prediction rating of a sample of movies. Our current research involves creating more fine-grained segments and segment-specific variations of prediction methods to further improve prediction accuracy.

Context-aware information retrieval helps providing resources that are relevant to the current situation of users. In many work environments, carrying out a task demands massive information access and management. Context-aware computing in such settings can reduce the need for manual information retrieval and assist the users in bringing forward relevant resources and hence decreasing the time and effort needed to manage and update the information.
So far, research in context-aware computing has mainly focused on adapting the devices and systems to the individual user’s need or behaviour. The system detects different patterns of a user’s work and adapts accordingly. However, in a collaborative work environment such as a hospital, adaptive information retrieval goes beyond covering the need of individuals, as clinical tasks often involve several users working concurrently sharing systems, devices and documents.
This thesis proposes an approach to the problem of context-aware information retrieval in multi-user collaborative environments with public shared devices. We identify three sub problems to be addressed;
1) detection of the situation in which the device is present; 2) recognition of sequential multiple concurrent activities in the observable space of the device; and 3) adaptation of the device to present the relevant information to current situation.
For the problem of detecting the situation of a device, we argue that in order to provide more precise information adaptation on different devices spread in a ubiquitous shared environment, the context of a device should be weighted. This can be done by recognizing not only the contextual elements related to that device (e.g., location and time) but also the situation pattern in which the device is present. For this, we introduce a method called ‘L-P-A Walk’ that identifies such situation patterns in the observable space of a device and helps weighting context elements that matter for that situation.
For the problem of activity recognition, we address the issues of i) multiple concurrent activities and ii) sequential dependency between activities. For the former, we propose joint- and parallel-learning mod els; and to address the latter, we add virtual and historical evidence as features to the learning models. We perform classification on the data and evaluate the output by proposing a distance based method. The best performance is obtained in parallel learning with historical evidence.
For the problem of information adaptation, we point to the fact that most real world situations have been experienced at least once before either in the same or a different setting. We argue that despite slight differences, there is always a most similar situation to the current one that can provide an initial set of handling or actions that might also be relevant to the new situation. This initial set is then updated, evolved, and adapted to the specific characteristics/profile of the current situation. By incorporating collaborative filtering, we dynamically provide most relevant types of information that has been used in similar
situations. An evaluation of our approach with clinicians shows
that the proposed mechanism is able to i) incrementally build and
update the model of relevant information for every situation based
on similar past cases and ii) incorporate users’ information choices as implicit feedback and retrain the model to provide more satisfactory information assistance.

Recommender systems are extensively seen as an effective means to combat information overload, as they redound us both narrow down the number of items to choose. They are seen as assistance us make better decisions at a lower transaction cost. Hence, recommender systems have become omnipresent in e-commerce and are also increasingly used in services in different other domains both online and offline where the number of items exceeds our potentiality to consider them all individually. The research papers recommender systems are software applications or systems that help individual users to discover the most relevant research papers to their needs. These systems use filtering techniques to create recommendations. These techniques are categorized majorly into collaborative-based filtering, content-based technique, and hybrid algorithm. In addition, they assist in decision making by providing product information both personalized and non-personalized, summarizing community opinion, search research papers, and providing community critiques. As a result, recommender systems have been shown to ameliorate the decision.

—Social influence plays an important role in product marketing. However, it has rarely been considered in traditional recommender systems. In this paper we present a new paradigm of recommender engine which can utilize information in social networks, including user preferences, item's general acceptance, and influence from social friends. A probabilistic model is developed to make personalized recommendations from such information. Presently human is encompassed by a colossal measure of data on the web. That highlights the continuous need of recommendation or suggestion systems in the different areas. Tragically cold start problem is still a critical issue in these systems on new clients and new items. So we are using social network site and adding customers profile in it and that added data as interest of someone is using over e-commerce site for recommendation. We are solving cold star problem and short life resources problem in this paper.

With the boom in IT technology, the data sets used in application are more and more larger and are
described by a huge number of attributes, therefore, the feature selection become an important discipline in
Knowledge discovery and data mining, allowing the experts to select the most relevant features to improve
the quality of their studies and to reduce the time processing of their algorithm. In addition to that, the data
used by the applications become richer. They are now represented by a set of complex and structured
objects, instead of simple numerical matrixes. The purpose of our algorithm is to do feature selection on
rich data, called Boolean Symbolic Objects (BSOs). These objects are described by multivalued features.
The BSOs are considered as higher level units which can model complex data, such as cluster of
individuals, aggregated data or taxonomies. In this paper we will introduce a new feature selection
criterion for BSOs, and we will explain how we improved its complexity.

This paper presents the design and implementation of a mobile application along with a web server for geo-tagging favorite and interesting places and sharing them with the community. The design and architecture shows some key aspects and issues concerning this kind of system. The mobile application is implemented in J2ME and tested on GPS enabled Nokia phones and the web server is implemented on cloud infrastructure implementation, the Google App Engine. The system was evaluated with real devices and a proof of concept was made that applications such as Place-Tags has its place in the mobile world.

Nowadays, many companies through the world wide web like YouTube, Netflix, Aliexpress and Amazon, provide personalized services as recommendations. Recommender systems use the related information about products or services to suggest the most relevant of them to particular users. The recommendation is usually made based on the prediction of the users' constraints and interests. Despite that the most of the existing recommender systems give accurate recommendation results, they do not provide explainable recommendation support. Therefore, in this paper we propose a new effective model-based trust collaborative filtering for explainable recommendations that aims not only to improve the quality of recommendation but also to provide an efficient support for explainable recommendations based on trustworthiness modeling. Our solution can both ensure how the item is recommended and why it is recommended. The proposed method is evaluated on Amazon Instant Video dataset in terms of RMSE.

The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document and are linked to publications on ResearchGate, letting you access and read them immediately. Abstract—One of the concerns users have to confronted when using IPTV system is information overload that makes it difficult for them to find a suitable content according to their personal preferences. Recommendation service is one of the most widely adopted technologies to alleviating this problem; these services intend to provide people with referrals of items they will appreciate based upon their preferences. IPTV users must ensure their sensitive preferences collected by any recommendation service are properly secured. In this work, we introduce a framework for private recommender service based on Enhanced Middleware for Collaborative Privacy (EMCP). EMCP executes a two-stage concealment process that gives the user a complete control on the privacy level of his profile. We utilize trust mechanism to augment recommendation's accuracy and privacy. Trust heuristic spot users whom are trustworthy with respect to the user requesting recommendation (target-user). Later, the neighbourhood formation is calculated using proximity metrics based on these trustworthy users. Finally, Users submit their profiles in an obfuscated form without revealing any information about their data, and the computation of recommendations proceeds over the obfuscated data using secure multi-party computation protocol. We expand the obfuscation scope from single obfuscation level for all users to arbitrary obfuscation levels based on trustworthy between users. In other words, we correlate the obfuscation level with different trust levels, so the more trusted a target user is the less obfuscation copy of users' profile he can access. We also provide an IPTV network scenario and experimentation results. Our results and analysis shows that our two-stage concealment process not only protect the users' privacy, but also can maintain the recommendations accuracy.