Research background: In a modern economy, full of complexities, ensuring a business' financial stability, and increasing its financial performance and competitiveness, has become especially difficult. Then, monitoring the company's financial situation and predicting its future development becomes important. Assessing the financial health of business entities using various models is an important area in not only scientific research, but also business practice. Purpose of the article: This study aims to predict the bankruptcy of companies in the engineering and automotive industries of the Slovak Republic using a multilayer neural network and logistic regression. Importantly, we develop a novel an early warning model for the Slovak engineering and automotive industries, which can be applied in countries with undeveloped capital markets. Methods: Data on the financial ratios of 2,384 companies were used. We used a logistic regression to analyse the data for the year 2019 and designed a logistic model. Meanwhile, the data for the years 2018 and 2019 were analysed using the neural network. In the prediction model, we analysed the predictive performance of several combinations of factors based on the industry sector, use of the scaling technique, activation function, and ratio of the sample distribution to the test and training parts. Findings & value added: The financial indicators ROS, QR, NWC/A, and PC/S reduce the likelihood of bankruptcy. Regarding the value of this work, we constructed an optimal network for the automotive and engineering industries using nine financial indicators on the input layer in combination with one hidden layer. Moreover, we developed a novel prediction model for bankruptcy using six of these indicators. Almost all sampled industries are privatised, and most companies are foreign owned. Hence, international companies as well as researchers can apply our models to understand their financial health and sustainability. Moreover, they can conduct comparative analyses of their own model with ours to reveal areas of model improvements.

The digital economy, driven by innovative technologies and artificial intelligence (AI), is transforming economic systems and increasing the demand for accurate assessments of digital competitiveness. This study addresses the inconsistencies in country rankings derived from global digital indices and aims to determine whether these rankings differ due to methodological variations. It also examines whether the rankings correlate significantly across different evaluation frameworks. The research focuses on 29 European countries and analyzes rankings from four widely recognized indices: the World Digital Competitiveness Ranking (WDCR), Network Readiness Index (NRI), AI Readiness Index (AIRI), and Digital Quality of Life Index (DQLI). To assess the consistency and variability in rankings from 2019 to 2024, the study applies Friedman’s ANOVA and Kendall’s coefficient of concordance. The results demonstrate strong correlations at the level of country rankings, indicating a high degree of consistency, but also confirm statistically significant differences in rankings among the indices, which reflect the diversity of their conceptual foundations. Countries such as Finland, the Netherlands, and Denmark consistently achieve top rankings, indicating convergence, while more variability is observed in indices like the DQLI. These findings highlight the importance of rank-based, multidimensional assessments in evaluating digital competitiveness. They support the use of such assessments as policy tools for monitoring progress, identifying gaps, and promoting inclusive digital development.

Forecasting using historical time series data has become increasingly important in today’s world. This paper aims to assess the potential for stable positive development within the wholesale and retail trade sector (SK NACE Section G) and the operations of HORTI, Ltd.( Košice, Slovakia), a company within this industry (SK NACE 46.31—wholesale of fruit and vegetables) by predicting three financial indicators: costs, revenues, and earnings before taxes (EBT) (or earnings after taxes (EAT)). We analyze quarterly data from Q1 2009 to Q4 2023 taken from the sector and monthly data from January 2013 to December 2022 for HORTI, Ltd. Through time series analysis, we aim to identify the most suitable model for forecasting the trends in these financial indicators. The study demonstrates that simple legacy forecasting methods, such as exponential smoothing and Box–Jenkins methodology, are sufficient for accurately predicting financial indicators. These models were selected for their simplicity, interpretability, and efficiency in capturing stable trends, and seasonality, especially in sectors with relatively stable financial behavior. The results confirm that traditional Holt–Winters’ and Autoregressive Integrated Moving Average (ARIMA) models can provide reliable forecasts without the need for more complex approaches. While advanced methods, such as GARCH or machine learning, could improve predictions in volatile conditions, the traditional models offer robust, interpretable results that support managerial decision-making. The findings can help managers estimate the financial health of the company and assess risks such as bankruptcy or insolvency, while also acknowledging the limitations of these models in predicting large shifts due to external factors or market disruptions.

This paper presents a cluster analysis of 20 spa enterprises operating in Slovakia, based on key financial indicators for the years 2018 and 2023. A comparative time-based approach was adopted to capture changes in financial performance over time. The primary objective is to group the spas into homogeneous clusters to better understand their financial performance and strategic positioning. Ten financial indicators were selected across five dimensions: profitability (return on assets, return on sales), efficiency (assets turnover), cost efficiency (personnel cost ratio, cost-to-sales ratio, return on costs), liquidity (net working capital, current ratio), and indebtedness (equity to total liabilities ratio, debt ratio). Hierarchical cluster analysis—a widely used statistical method in unsupervised machine learning and a foundational technique in artificial intelligence—was employed, serving as a robust tool for data-driven decision making. The analysis identified distinct clusters of spas with similar financial characteristics. The results reveal meaningful segmentation that can inform resource allocation, performance benchmarking, and strategic planning. The findings provide spa managers, investors, and policy makers with a clearer understanding of financial patterns in the Slovak spa sector and offer practical implications for enhancing competitiveness and operational effectiveness.

Bankruptcy prediction is currently a widely researched topic, as it typically results from a chain of negative events. Logistic Regression (LR) is one of the standard prediction tools; however, with advances in technology, machine learning (ML) methods are gaining prominence and demonstrating improvements in performance and accuracy. It remains inconclusive whether ML methods significantly outperform traditional approaches such as LR in bankruptcy prediction. In this study, we identified the most commonly applied basic ML techniques—namely, Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), and Decision Trees (DTs)—which are frequently used in the literature for classification tasks. These methods were selected for empirical comparison with LR to evaluate their relative predictive performance and potential advantages in bankruptcy forecasting. In the EU, small and medium-sized enterprises (SMEs) constitute more than 99% of the economy; however, only a few survive beyond five years. This study examines bankruptcy prediction in the specific context of the Slovak Republic, using a sample of 2754 SME manufacturing enterprises from 2020 to 2021 and 3158 from 2022 to 2023. All models show good predictive performance; however, the small statistical difference between the results does not conclusively demonstrate the superiority of ML methods over LR.