Результаты поиска 1 - 2 из 2
Начало | Пред. | 1 | След. | Конец

Structural approach to company management in extraordinary situations

Shchetinin E.Yu. doctor of physical and mathematical sciences, professor, Moscow State Technological University “Stankin”

Journal: Financial Analytics: Science and Experience, #6, 2009

In the process of this work structural approach to evaluation of results of activity of company allows considering influence of external factors to its business structure and changes that happen to it in the result of this influence. The suggested methods of prevention and overcoming of extraordinary situations may be widely used in the analysis of the current everyday and fundamental qualitative analysis of economic condition of credit and financial organizations.

On methods to improve the reliability of recommender systems based on user clustering

Shchetinin E.Yu. Financial University under Government of Russian Federation, Moscow, Russian Federation ( )

Journal: Economic Analysis: Theory and Practice, #7, 2019

Subject The growing popularity of e-commerce services is increasingly attracting the attention of their users to the services of recommendation engines. Collaborative filtering is one of the well-known recommendation methods that help customers select products of their interest. However, recommender systems are open to malicious attacks to promote or discredit certain products. For instance, the so-called shilling attacks cause a significant change in the rating of products in the social network, thereby causing significant material and moral damage.
Objectives The purpose of the study is to increase the robustness of e-commerce systems and protect them against any manipulation by attackers and unscrupulous users; to develop computer algorithms to prevent the intrusion of fake recommendations into the recommendation system.
Methods The study employs data mining techniques and machine learning methods.
Results The paper considers characteristics of shilling attacks, describes their main models and parameters, and offers effective methods to detect fake profiles. I developed a computer algorithm of recommendations based on clustering as a powerful method to counter shilling attacks in social networks. I investigated its resistance to shilling attacks being the most popular among intruder, and analyzed the influence of various attack parameters on the results of its work.
Conclusions Computer simulation of shilling attacks and analysis of their impact on the forecast of shift in recommendations showed that the algorithm is resistant to shilling attacks without significant impact of introduced malicious profiles on the work of the recommender system.

Результаты поиска 1 - 2 из 2
Начало | Пред. | 1 | След. | Конец

Отсортировано по релевантности | Сортировать по дате