Abstract: Cold-start is a notoriously difficult problem which
can occur in recommendation systems, and arises when there is
insufficient information to draw inferences for users or items. To
address this challenge, a contextual bandit algorithm – the Fast
Approximate Bayesian Contextual Cold Start Learning algorithm
(FAB-COST) – is proposed, which is designed to provide improved
accuracy compared to the traditionally used Laplace approximation
in the logistic contextual bandit, while controlling both algorithmic
complexity and computational cost. To this end, FAB-COST uses
a combination of two moment projection variational methods:
Expectation Propagation (EP), which performs well at the cold
start, but becomes slow as the amount of data increases; and
Assumed Density Filtering (ADF), which has slower growth of
computational cost with data size but requires more data to obtain an
acceptable level of accuracy. By switching from EP to ADF when
the dataset becomes large, it is able to exploit their complementary
strengths. The empirical justification for FAB-COST is presented, and
systematically compared to other approaches on simulated data. In a
benchmark against the Laplace approximation on real data consisting
of over 670, 000 impressions from autotrader.co.uk, FAB-COST
demonstrates at one point increase of over 16% in user clicks. On
the basis of these results, it is argued that FAB-COST is likely to
be an attractive approach to cold-start recommendation systems in a
variety of contexts.
Abstract: The world is expected to experience growth in the number of ageing population, and this will bring about high cost of providing care for these valuable citizens. In addition, many of these live with chronic diseases that come with old age. Providing adequate care in the face of rising costs and dwindling personnel can be challenging. However, advances in technologies and emergence of the Internet of Things are providing a way to address these challenges while improving care giving. This study proposes the integration of recommendation systems into homecare to provide real-time recommendations for effective management of people receiving care at home and those living with chronic diseases. Using the simplified Training Logic Concept, stakeholders and requirements were identified. Specific requirements were gathered from people living with cancer. The solution designed has two components namely home and community, to enhance recommendations sharing for effective care giving. The community component of the design was implemented with the development of a mobile app called Recommendations Sharing Community for Aged and Chronically Ill People (ReSCAP). This component has illustrated the possibility of real-time recommendations, improved recommendations sharing among care receivers and between a physician and care receivers. Full implementation will increase access to health data for better care decision making.
Abstract: Most movie recommendation systems have been developed for customers to find items of interest. This work introduces a predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from thousands of customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.
Abstract: Rating prediction is an important problem for recommender systems. The task is to predict the rating for an item that a user would give. Most of the existing algorithms for the task ignore the effect of negative ratings rated by users on items, but the negative ratings have a significant impact on users’ purchasing decisions in practice. In this paper, we present a rating prediction algorithm based on factorization machines that consider the effect of negative ratings inspired by Loss Aversion theory. The aim of this paper is to develop a concave and a convex negative disgust function to evaluate the negative ratings respectively. Experiments are conducted on MovieLens dataset. The experimental results demonstrate the effectiveness of the proposed methods by comparing with other four the state-of-the-art approaches. The negative ratings showed much importance in the accuracy of ratings predictions.
Abstract: Recommendation systems are widely used in
e-commerce applications. The engine of a current recommendation
system recommends items to a particular user based on user
preferences and previous high ratings. Various recommendation
schemes such as collaborative filtering and content-based approaches
are used to build a recommendation system. Most of current
recommendation systems were developed to fit a certain domain such
as books, articles, and movies. We propose1 a hybrid framework
recommendation system to be applied on two dimensional spaces
(User × Item) with a large number of Users and a small number
of Items. Moreover, our proposed framework makes use of both
favorite and non-favorite items of a particular user. The proposed
framework is built upon the integration of association rules mining
and the content-based approach. The results of experiments show
that our proposed framework can provide accurate recommendations
to users.
Abstract: The proliferation of user-generated content (UGC) results in huge opportunities to explore event patterns. However, existing event recommendation systems primarily focus on advanced information technology users. Little work has been done to address novice and low-literacy users. The next billion users providing and consuming UGC are likely to include communities from developing countries who are ready to use affordable technologies for subsistence goals. Therefore, we propose a design framework for providing event recommendations to address the needs of such users. Grounded in information integration theory (IIT), our framework advocates that effective event recommendation is supported by systems capable of (1) reliable information gathering through structured user input, (2) accurate sense making through spatial-temporal analytics, and (3) intuitive information dissemination through interactive visualization techniques. A mobile pest management application is developed as an instantiation of the design framework. Our preliminary study suggests a set of design principles for novice and low-literacy users.
Abstract: Recommender systems are usually regarded as an
important marketing tool in the e-commerce. They use important
information about users to facilitate accurate recommendation. The
information includes user context such as location, time and interest
for personalization of mobile users. We can easily collect information
about location and time because mobile devices communicate with the
base station of the service provider. However, information about user
interest can-t be easily collected because user interest can not be
captured automatically without user-s approval process. User interest
usually represented as a need. In this study, we classify needs into two
types according to prior research. This study investigates the
usefulness of data mining techniques for classifying user need type for
recommendation systems. We employ several data mining techniques
including artificial neural networks, decision trees, case-based
reasoning, and multivariate discriminant analysis. Experimental
results show that CHAID algorithm outperforms other models for
classifying user need type. This study performs McNemar test to
examine the statistical significance of the differences of classification
results. The results of McNemar test also show that CHAID performs
better than the other models with statistical significance.
Abstract: This study examines the issue of recommendation
sources from the perspectives of gender and consumers- perceived
risk, and validates a model for the antecedents of consumer online
purchases. The method of obtaining quantitative data was that of the
instrument of a survey questionnaire. Data were collected via
questionnaires from 396 undergraduate students aged 18-24, and a
multiple regression analysis was conducted to identify causal
relationships. Empirical findings established the link between
recommendation sources (word-of-mouth, advertising, and
recommendation systems) and the likelihood of making online
purchases and demonstrated the role of gender and perceived risk as
moderators in this context. The results showed that the effects of
word-of-mouth on online purchase intentions were stronger than those
of advertising and recommendation systems. In addition, female
consumers have less experience with online purchases, so they may be
more likely than males to refer to recommendations during the
decision-making process. The findings of the study will help
marketers to address the recommendation factor which influences
consumers- intention to purchase and to improve firm performances to
meet consumer needs.