https://repository.hneu.edu.ua/handle/123456789/178 2026-05-09T09:48:46Z 2026-05-09T09:48:46Z Minukhin S. V. Bukhalo V. O. https://repository.hneu.edu.ua/handle/123456789/39859 2026-05-07T18:15:25Z 2026-01-01T00:00:00Z

Назва: A study of the impact of the weighted reciprocal rank fusion method on the quality of recommender systems Автори: Minukhin S. V.; Bukhalo V. O. Короткий огляд (реферат): Providing high-quality recommendations is an important factor in increasing the level of audience engagement, since under conditions of rapid growth in the volume of available information, a significant part of which is presented in the form of implicit feedback, recommender systems ensure the effective selection and ranking of items according to individual user preferences. CF is one of the most widespread strategies for constructing such systems and generates recommendations based on the analysis of user interactions with similar behaviour patterns, which makes it possible to identify not only obvious but also unexpected potentially relevant items. During the generation of recommendations by different CF algorithms, recommendation lists for each user are produced that differ in the composition and order of items, which is caused by differences in the principles of determining the relevance of items. Since CF algorithms produce distinct recommendation lists for each user, it is appropriate to apply the WRRF method, which ensures the aggregation of rankings generated by algorithms in order to construct a single ranked recommendation list of higher quality. The purpose of this work is to study the influence of the WRRF method on the quality of generation and ranking of recommendation lists obtained as a result of the pairwise combination of CF algorithms through rank aggregation of items. According to the results of the experimental study, it has been established that the use of the WRRF method in the vast majority of cases ensures an improvement in recommendation quality compared with the best algorithm in the corresponding pair. The experimental evaluation was carried out using six CF algorithms on three datasets transformed into the implicit feedback format. The obtained results can be used in the development and improvement of industrial recommender systems in order to increase the quality of recommendation ranking without significant complication of their software architecture.

2026-01-01T00:00:00Z Skorin Yu. https://repository.hneu.edu.ua/handle/123456789/39787 2026-05-05T10:04:05Z 2025-01-01T00:00:00Z

Назва: Improvement of the automated NLP system as a factor in improving the quality of marketing strategy formation Автори: Skorin Yu. Короткий огляд (реферат): Natural language processing in company marketing is transforming data analytics, offering new opportunities to understand customers and optimize strategies. Natural language processing simplifies processes such as sentiment analysis, segmentation, and ad targeting. It is important to consider data accuracy, security, and query management skills training for effective use of technology. One of the main challenges in marketing analytics is the transformation of initial numerical data into understandable and useful conclusions for humans. The way to solve the problem are natural language processing technologies and generative artificial intelligence, which allow you to turn complex data into accessible and useful information for work. Traditional manual analysis of reviews in marketing analytics has long ceased to meet modern business requirements, because it requires huge human resources, which makes the process extremely costly. Natural language processing offers a solution to this problem through the use of algorithms capable of automatically analyzing the semantics of the text, determining the tone of statements, and isolating key topics from large data sets. The purpose of this study is to develop a system of automated analysis of user reviews based on the developed effective methods and models for automated analysis of user reviews in the field of marketing of companies using natural speech processing technologies. The paper describes the problem to be solved and formulates a scientific task; analyzes approaches, methods and models for solving research problems; sets research tasks, analyzes theoretical approaches to solving research problems; considers theoretical aspects of natural language processing; investigates various models and algorithms for analyzing feedback, and also conducts an experimental assessment of their effectiveness on real data; models, algorithms and analysis of their adequacy in solving research problems; methodological support for the organization of research is being improved. The results of the study can be used to develop software solutions that will allow companies to better understand the needs of their customers, quickly respond to problems and improve the quality of their products and services.

2025-01-01T00:00:00Z Skorin Yu. Petrenko B. https://repository.hneu.edu.ua/handle/123456789/39786 2026-05-05T09:59:43Z 2025-01-01T00:00:00Z

Назва: Application of natural language processing to automate the analysis of user feedback Автори: Skorin Yu.; Petrenko B. Короткий огляд (реферат): The purpose of the research is to develop a system for automated analysis of user feedback based on natural language processing methods to identify sentiments, key aspects and themes. The relevance of the research topic is due to the growing need for businesses in effective tools for analyzing large volumes of text data, which would allow extracting valuable insights from user feedback and transforming them into specific recommendations for improving products and services. This topic is of particular importance in the context of e-commerce, services and software development, where the quality and speed of response to user feedback directly affect the competitiveness of companies. Research methods include machine learning, deep neural networks, statistical text analysis methods and methods for assessing the quality of models. Classical algorithms, neural network models, transformer architectures are used. The statistical significance of the results obtained was experimentally confirmed and recommendations for selecting models for various scenarios were developed. The relevance of the research topic is due to the growing business need for effective tools for analyzing large volumes of text data, which would allow extracting valuable insights from user reviews and transforming them into specific recommendations for improving products and services. The research results can be used in e-commerce, service companies, software development, marketing, and analytics to automate review analysis and identify trends in large volumes of text data.

2025-01-01T00:00:00Z Скорін Ю. І. https://repository.hneu.edu.ua/handle/123456789/39785 2026-05-05T09:53:52Z 2025-01-01T00:00:00Z

Назва: Застосування штучного інтелекту в автоматизованих системах управління фінансовими ризиками Автори: Скорін Ю. І. Короткий огляд (реферат): У статті викладено результати комплексного дослідження застосування технологій штучного інтелекту в автоматизованих системах управління фінансовими ризиками для підвищення ефективності прогнозування, зниження рівня кредитних збитків і вдосконалення процесів прийняття рі-шень у банківській сфері та розроблення аналітичної моделі прогнозу-вання ризику на основі сучасних алгоритмів машинного навчання.

2025-01-01T00:00:00Z