One of the key areas of contemporary marketing is the formulation of a pricing strategy, which is one of the four pillars of the traditional marketing mix. One way to implement this strategy is through dynamic pricing. It is currently gaining popularity in many industries for two reasons. Firstly, it is possible, easy, and cheap to collect information about transactions and customers. Secondly, machine learning mechanisms, for which these data are essential, are becoming widely available. The aim of this article is to propose a dynamic pricing method for the e-commerce industry. To achieve this goal, machine learning methods such as the Naive Bayes classifier, support vector machines (linear and nonlinear), decision trees, and the k-nearest neighbor algorithm were used. The empirical results indicate that the linear support vector machine achieved the highest accuracy (86.92%), demonstrating the model’s effectiveness in classifying pricing decisions. This article aligns with two leading research trends in dynamic pricing: personalized dynamic pricing (the target model considers customer-related criteria) and the development of systems to assist managers in optimizing pricing strategies to increase revenues (using machine learning methods). This article presents a literature review on dynamic pricing and then discusses the machine learning methods applied. In the final part of this article, verification of the developed dynamic pricing method using real-world conditions is presented.

The main purpose of the article is to develop a method for predicting the type of organizational culture using machine learning. The method is to be based on the popular OCAI survey by Cameron and Quinn (2022). To achieve the main goal of the study, selected machine learning algorithms were utilized. The developed method primarily reduces cognitive effort both on the part of respondents to traditional organizational culture survey sheets and on the part of researchers who analyze the results of traditional organizational culture diagnosis sheets. The reduction in cognitive effort on the respondents' side is due to the fact that they do not have to distribute 100 points for each of the six questions for each type of organizational culture. In the developed method, the only task of the respondents is to indicate the dominant type of organizational culture in each of the six criteria (questions in the survey). An additional purpose of the article is to present machine learning as a useful quantitative instrument for solving problems that occur in the theory and practice of management and quality sciences.

The first objective of the article is to develop a method for predicting the level of sustainability in family firms based on the dimensions of socioemotional wealth. To achieve this goal, the following machine learning algorithms were employed: Support Vector Regression (Linear Kernel), Support Vector Regression (Radial Basis Function Kernel), Decision Tree Regressor (DTR), K-Neighbours Regressor (KNR), Random Forest Regressor (RF), and Linear Regression (LR). The second objective was to determine the impact of individual socioemotional wealth dimensions on the sustainability index of family businesses. To this end, the Permutation Feature Importance (PFI) method, classified under Explainable Artificial Intelligence (XAI), was used. The study’s results on Polish family firms revealed that the SEW dimension most strongly influencing the sustainability index is the active promotion of initiatives for the local community.

The growing use of AI-supported recruitment systems raises concerns related to model opacity, auditability, and ethically sensitive decision-making, despite their predictive potential. In human resource management, there is a clear need for recruitment solutions that combine analytical effectiveness with transparent and explainable decision support. Existing approaches often lack coherent, multi-layered architectures integrating expert knowledge, machine learning, and interpretability within a single framework. This article proposes an interpretable, multi-layered recruitment model designed to balance predictive performance with decision transparency. The framework integrates an expert rule-based screening layer, an unsupervised clustering layer for structuring candidate profiles and generating pseudo-labels, and a supervised classification layer trained using repeated k-fold cross-validation. Model behavior is explained using SHAP, while Necessary Condition Analysis (NCA) is applied to diagnose minimum competency thresholds required to achieve a target quality level. The approach is demonstrated in a Data Scientist recruitment case study. Results show the predominance of centroid-based clustering and the high stability of linear classifiers, particularly logistic regression. The proposed framework is replicable and supports transparent, auditable recruitment decisions.

The aim of the paper is to explore the relationship between skills shortages and the adoption of artificial intelligence (AI) in organizational contexts. While existing literature often considers AI as a substitute for labor, this study addresses a less examined perspective – AI adoption as a strategic response to persistent difficulties in recruiting highly educated and skilled workers. Drawing on theoretical frameworks from human capital theory and labor economics, and using empirical data from small and medium-sized enterprises (SMEs) across 34 developed countries, the analysis demonstrates that labor shortages – particularly at the bachelor’s and master’s education levels – significantly increase the probability of AI implementation. The paper shows that AI is not merely a labor-saving technology, but a means of maintaining competitiveness and scalability under conditions of human capital constraints. However, the adoption of AI is not uniform: it depends on internal readiness and sectoral dynamics, pointing to a paradox: while AI can mitigate talent shortages, it also introduces new demands for technical capabilities. These insights suggest that addressing the talent gap requires integrated strategies across organizational design, workforce development, and public policy.

Digital traces are increasingly used as alternatives to self-reports in research on human attributes. Emails, collaboration platforms, device logs, and wearable sensors appear to provide continuous, behaviourally grounded access to constructs such as engagement, stress, productivity, and turnover intentions. This article argues that the apparent shift from subjective reports to objective behaviour is conceptually misleading: a digital record is neither the behaviour that generated it nor the construct attributed to a person. It re-constructs an algorithmic measurement pipeline linking the target construct, context, behaviour, recording system, digital record, computational representation, training label, model output, and interpreted measurement claim. The analysis identifies four inferential gaps: recording, representation, proxy-label, and interpretation. It also formulates the invasive proxy paradox: a method presented as a more objective substitute for self-report may be more intrusive while remaining epistemically dependent on self-report labels. The article proposes a dual-warrant framework, according to which legitimate algorithmic measurement requires both epistemic warrant for construct interpretation and normative warrant for evidence generation and use. The employee-engagement case demonstrates how surveillance and power asymmetries can undermine both warrants by altering the behaviour from which data are generated.