Marharyta Aleksandrova

Fuzzy Clustering with Prototype Extraction for Census Data Analysis

Not long ago primary census data became available to publicity. It opened qualitatively new perspectives not only for researchers in demography and sociology, but also for those people, who somehow face processes occurring in society.

Identifying representative users in matrix factorization-based recommender systems: application to solving the content-less new item cold-start problem

Matrix factorization has proven to be one of the most accurate recommendation approaches. However, it faces one major shortcoming: the latent features that result from the factorization are not directly interpretable. Providing interpretation for these features is important not only to help explain the recommendations presented to users, but also to understand the underlying relations between the users and the items. This paper consists of 2 contributions. First, we propose to automatically interpret features as users, referred to as representative users. This interpretation relies on the study of the matrices that result from the factorization and on their link with the original rating matrix. Such an interpretation is not only performed automatically, as it does not require any human expertise, but it also helps to explain the recommendations. The second proposition of this paper is to exploit this interpretation to alleviate the content-less new item cold-start problem. The experiments conducted on several benchmark datasets confirm that the features discovered by a Non-Negative Matrix Factorization can be interpreted as users and that representative users are a reliable source of information that allows to accurately estimate ratings on new items. They are thus a promising way to solve the new item cold-start problem.

Prediction of nocturnal hypoglycemia by an aggregation of previously known prediction approaches

BACKGROUND AND OBJECTIVE Nocturnal hypoglycemia (NH) is common in patients with insulin-treated diabetes. Despite the risk associated with NH, there are only a few methods aiming at the prediction of such events based on intermittent blood glucose monitoring data and none has been validated for clinical use. Here we propose a method of combining several predictors into a new one that will perform at the level of the best involved one, or even outperform all individual candidates. METHODS The idea of the method is to use a recently developed strategy for aggregating ranking algorithms. The method has been calibrated and tested on data extracted from clinical trials, performed in the European FP7-funded project DIAdvisor. Then we have tested the proposed approach on other datasets to show the portability of the method. This feature of the method allows its simple implementation in the form of a diabetic smartphone app. RESULTS On the considered datasets the proposed approach exhibits good performance in terms of sensitivity, specificity and predictive values. Moreover, the resulting predictor automatically performs at the level of the best involved method or even outperforms it. CONCLUSION We propose a strategy for a combination of NH predictors that leads to a method exhibiting a reliable performance and the potential for everyday use by any patient who performs self-monitoring of blood glucose.

Can Latent Features Be Interpreted as Users in Matrix Factorization-Based Recommender Systems?

Matrix factorization has proven to be one of the most accurate recommendation approach. However, it faces one main shortcoming: the latent features that result from factorization, and that represent the underlying relation between users and items, are not directly interpretable. Some works focused on their interpretation, particularly with non-negative matrix factorization. In these works, features are viewed as groups of users, groups of items or as attributes of items, but such interpretations require human expertise. In this paper, we propose to interpret features as users, referred to as representative users. This interpretation relies on the study of the matrices that result from the factorization and on their link with the original rating matrix. Such an interpretation is not only performed automatically, as it does not require any human expertise, but it helps also to explain the recommendations made to users. In addition, we see it as a way to alleviate the new item cold-start problem, without requiring any information about the content of the items. The experiments conducted on several benchmark datasets confirm that the features discovered by a non-negative matrix factorization can be actually interpreted as users and that the representative users (the interpretations of the features), are a reliable source of information that allows to accurately estimate ratings on new items. They are thus a promising way to solve the new item cold-start problem.

Contrast classification rules for mining local differences in medical data

In this paper, we formally prove that the classification rules formed on the basis of contrast patterns are guaranteed to be of a high quality. We propose to use the new ‘Sets of Contrasting Rules’ pattern for the identification of local differences between the classes of the dataset. Being essentially a contrast pattern formed of several classification rules, ‘Sets of Contrasting Rules’ pattern is guaranteed to have the values of lift and conviction superior to 1. This makes it being valuable for knowledge discovery in such domains as healthcare.

Comparative analysis of neighborhood-based approache and matrix factorization in recommender systems

Unlike other works, this paper aims at searching a connection between two most popular approaches in recommender systems domain: Neighborhood-based (NB) and Matrix Factorization-based (MF). Provided analysis helps better understand advantages and disadvantages of each approach as well as their compatibility. While NB relies on the ratings of similar users to estimate the rating of a user on an item, MF relies on the identification of latent features that represent the underlying relation between users and items. However, as it was shown in this paper, if latent features of Non-negative Matrix Factorization are interpreted as users, the processes of rating estimation by two methods become similar. In addition, it was shown through experiments that in this case elements of NB and MF are highly correlated. Still there is a major difference between Matrix Factorization-based and Neighborhood-based approaches: the first one exploits the same set of base elements to estimate unknown ratings (the set of latent features), while the second forms different sets of base elements (in this case neighbors) for each user-item pair.