№ 12

Permanent URI for this collection

https://ir.kneu.edu.ua/handle/2010/46013

Browse

Browsing № 12 by Issue Date

Filter results by year or month
Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Comparative analysis of the effectiveness of dimensionality reduction algorithms and clustering methods on the problem of modelling economic growth
    (Київський національний економічний університет імені Вадима Гетьмана, 2023) Pozniak, Serhii; Позняк, Сергій Володимирович; Koliada, Yurii; Коляда, Юрій Васильович
    This article is devoted to the research of economic growth of countries by identifying patterns in historical data sets on macroeconomic indicators. Using machine learning techniques, namely cluster analysis methodology in combination with data transformation algorithms, in particular dimensionality reduction, groups of countries with similar patterns in the structure of the economy, availability of production factors, internal and external economic activity and development dynamics were formed. The novelty of the article is the approach to selecting optimal clustering and dimensionality reduction algorithms by quantifying the results of their work. The evaluation of the dimensionality reduction methods was carried out using the cumulative variance indicator, and the clustering methods were assessed based on the aggregate indicator proposed in the article, which combines the standardized Davies-Bouldin, Calinski-Harabasz indices and the Silhouette coefficient. According to calculations, among the 11 considered methods of dimensionality reduction, the most effective is the Kernel PCA algorithm, while among the 7 clustering methods, K-means is the most effective for this task with a given set of indicators. The study was conducted on 6 five-year time intervals from 1991 to 2020 with a focus on the Ukrainian economy. According to the research, Ukraine’s economy migrated from the “post-Soviet” cluster (first half of the 1990s) to the Eastern European cluster (second half of the 2010s) over the period under consideration, which indicates real economic growth and gradual integration with the European Union.
  • No Thumbnail Available
    Item
    Fuzzy clustering approach to portfolio management considering ESG criteria: empirical evidence from the investment strategies of the EURO STOXX Index
    (Київський національний економічний університет імені Вадима Гетьмана, 2023) Kaminskyi, Andrii; Nehrey, Maryna
    Environmental, social and governance (ESG) criteria are becoming increasingly important in the construction of investment portfolios. Analysis of the investment markets confirms that these criteria are being actively integrated into investment strategies. This paper presents our approach to incorporating ESG criteria into the portfolio construction process based on an index investment strategy. This strategy is enhanced by the inclusion of ESG criteria in the form of ESG scoring. Investment portfolio construction focuses on the application of three criteria: maximizing ESG score, minimizing risk and maximizing expected return. Our approach applies a fuzzy clustering toolkit to the set of index components. In the resulting fuzzy clusters, their core part (companies that do not belong to other clusters) and the fuzzy part are separated. The proposed investment strategy involves the construction of portfolios with a variation of the components of the fuzzy part. A VAWI (Value Added Weekly Index) curve is designed for each portfolio. The optimal strategy is implemented by constructing and reconstructing portfolios according to the upper line of the VAWI set. This investment strategy is demonstrated using the example of the EURO STOXX 50 index, which includes large companies from 11 Eurozone countries.
  • No Thumbnail Available
    Item
    Artificial intelligence tools for managing the behavior of economic agents at micro level
    (Київський національний економічний університет імені Вадима Гетьмана, 2023) Turlakova, Svitlana; Lohvinenko,Bohdan
    In modern business conditions, effective management of employee behavior is becoming a critical factor in ensuring competitive advantages and development of enterprises. AI tools, which are rapidly developing, provide new opportunities for managing the behavior of economic agents at the micro level and increasing the productivity of companies. To make the most effective use of AI in the outlined processes, there is a need to conduct research into the areas and possibilities of their application and impact on enterprise personnel. The methodology and mathematical model developed in the article, based on the use of theories of fuzzy sets, neural networks and Lefebvre reflexive control, allow to study the potential and prospects for using AI tools (on an example of SAP SuccessFactors) in managing the behavior of economic agents at the micro level, in particular in predicting the efficiency of employees at enterprise. It was concluded that the SAP SuccessFactors can evaluate the effectiveness of various personnel groups differently. This may occur due to insufficient adaptation of the models to the specifics of work and personal characteristics of employees of different productivity levels. Therefore, when using AI tools in the management of personnel behavior, it is important to consider such features and make individual settings for different groups of employee performance. This is a key aspect to avoid wrong management decisions that can affect the economic efficiency of the enterprise.