Matrix Factorisation is a recommendation approach that tries to understand what factors interest a user, based on his past ratings for items (products, movies, songs), and then use this factor information to predict future item ratings. A central limitation of this approach however is that it cannot capture how a user’s tastes have evolved beforehand; thereby ignoring if a user’s preference for...

Developing a pattern language is a non-trivial problem. A critical requirement is a method to support pattern writers with abstraction, so as they can produce generalised patterns. In this paper, we address this issue by developing a structured process of generalisation. It is important that this process is initiated through engaging participants in identifying initial patterns, i.e. directly d...

This paper deals with the modeling of the brushed DC motor used as a reinforced starter for a micro-hybrid automotive application. The aim of such a system, also called “stop-start”, is to stop a combustion engine when the vehicle pulls to a stop, and to restart it when the driver accelerates. A reinforced starter is able to ensure this new function in addition to the classical cold start. Then...

The JHU HLTCOE participated in the Entity Linking and Cold Start Knowledge Base tasks in this year’s Text Analysis Conference Knowledge Base Population evaluation. We have previously participated in TAC-KBP evaluations in 2009, 2010, 2011, and 2012. Our primary focus this year was on the Cold Start task; improvements to our existing KELVIN system included consolidating slot values for an entity...

Collaborative Filtering (CF) is a technique to generate personalised recommendations for a user from a collection of correlated preferences in the past. In general, the effectiveness of CF greatly depends on the amount of available information about the target user and the target item. The cold-start problem, which describes the difficulty of making recommendations when the users or the items a...

Recommender systems suffer from the new user problem, i.e., the difficulty to make accurate predictions for users that have rated only few items. Moreover, they usually compute recommendations for items just in one domain, such as movies, music, or books. In this paper we deal with such a cold-start situation exploiting cross-domain recommendation techniques, i.e., we suggest items to a user in...

Modern recommender systems model people and items by discovering or ‘teasing apart’ the underlying dimensions that encode the properties of items and users’ preferences toward them. Critically, such dimensions are uncovered based on user feedback, often in implicit form (such as purchase histories, browsing logs, etc.); in addition, some recommender systems make use of side information, such as...

We study the cold-start link prediction problem where edges between vertices is unavailable by learning vertex-based similarity metrics. Existing metric learning methods for link prediction fail to consider communities which can be observed in many real-world social networks. Because di↵erent communities usually exhibit di↵erent intra-community homogeneities, learning a global similarity metric...

The cold start problem, frequent with recommender systems, addresses the issue in cases where we don’t know enough about our users (e.g., the user hasn’t rated anything yet, or there are no user activities) in that specific domain. In our paper we present a simple and robust transfer learning approach where we model users’ behavior in a source domain, transferring that knowledge to a new, targe...

To make rating predictions, one of the most commonly used approach in recommender systems is the latent factor model. Despite its popularity, one of its drawbacks is that it only makes use of numeric ratings but ignores other resources, such as review texts. McAuley et al. [1] proposed a general framework to employ both numeric ratings and review texts, and showed their model can outperform the...