Journal of process management and new technologies

MACHINE LEARNING: TECHNIQUES, APPLICATIONS, AND METRICS FOR ENHANCED VEHICLE PERFORMANCE

Aadil Arshad FERHATH — Sat, 04 Oct 2025 08:18:31 +0200

Machine learning allows systems to autonomously learn from data and improve performance without direct programming, providing robust tools for identifying patterns, forecasting outcomes, and optimising complex processes. This paper offers a comprehensive overview of machine learning, beginning with an examination of its core categories: supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning. The review considers essential algorithms associated with each machine learning category, providing insights into their functions and real-world applications. The paper also discusses widely used evaluation metrics for regression models, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²), which are essential for assessing predictive performance and guiding model selection. The article examines numerous real-world applications of machine learning across various sectors, including healthcare, banking, transportation, marketing, and cybersecurity, illustrating how these technologies are transforming modern processes and delivering tangible benefits.

AN ANALYSIS OF THE DETERMINANTS AFFECTING THE PERFORMANCE OF MICROFINANCE INSTITUTIONS IN GHANA

Jane ARTHUR-SAM — Sat, 18 Oct 2025 23:58:03 +0200

Microfinance Institutions (MFIs) are crucial in providing services to the underprivileged, particularly those with limited incomes and the unorganized sector in a sustainable manner. In the Ghanaian business industry, these firms are primarily seen as vital institutions for progress against poverty and an excessive dependence on national and local governments. Thus, the goal of this study is to identify the factors affecting the performance of Microfinance institutions in Ghana. Multiple regression and descriptive statistics were used to analyze the secondary data gathered from the 133 MFIs in Ghana with SPSS. The study's conclusions showed that efficiency and liquidity have significantly positively impact on the firms' return on equity (ROE). Capital adequacy ratio (CAR) and non-performing loans (NPL) had no statistically significant effect on the Microfinance institutions' performance (ROE). Additionally, the study discovered a significant positive effect of CAR on the performance of the return on assets (ROA) on the MFIs. However, liquidity, efficiency and NPL had no statistical significant impact on the performance (ROA) of the companies. The research contributes to literature on the studies conducted on MFIs in Ghana and practically assists in improving and enhancing their performance. This study also promotes ways on how the government and stakeholders can support MFIs for a long-term sustainability and the economic growth in the country.

TOWARDS INTEGRATING FORENSIC ACCOUNTING IN UNIVERSITY CURRICULA: EVIDENCE FROM STUDENT PERCEPTIONS

Stefan MILOJEVIĆ, Tijana MATEJIĆ, Miloš MILOŠEVIĆ, Milan RESIMIĆ — Sun, 19 Oct 2025 00:12:12 +0200

The subject of this paper is the perception of students regarding the discipline known as forensic accounting. The aim of the paper is to identify the challenges related to the broader application of this discipline in management and information technology studies. The analysis was conducted on a sample of 70 management and IT students from the University of Belgrade, enabling a preliminary assessment of perception and the potential for improving educational and institutional mechanisms to further affirm forensic accounting in higher education and business practice. The obtained results were interpreted using descriptive statistics, Spearman’s correlation analysis, and exploratory factor analysis, aiming to identify latent dimensions that shape student attitudes toward this interdisciplinary field.

IMAGE PROCESSING BASED PLANT FERTILIZER SPRAYING ROBOT

Omkar KACHARE, Vandana KALE, Badri NARAYAN MOHAPATRA, Nikhil NEHE — Sun, 19 Oct 2025 01:18:00 +0200

The application of smart technologies in agriculture has transformed conventional farming practices, significantly increasing productivity and sustainability. In this research, we propose a novel method of agricultural automation through the development of an Autonomous Plant Spraying Robot. The system integrates Raspberry Pi and ESP32 microcontrollers along with servo motors to provide a flexible and robust solution for various agricultural operations. The Raspberry Pi functions as the central processing unit, offering substantial computational power and connectivity for real-time data processing and decision-making. The ESP32 microcontroller manages wireless communication and sensor integration, enabling remote monitoring and control of agricultural activities. Servo motors are employed for precise and efficient actuation, allowing the robot to carry out tasks such as spraying, irrigation, and harvesting with high accuracy and consistency. Key features of the project include modular design, scalability, and ease of customization. By leveraging open-source hardware and software platforms, the system remains adaptable and easily integrated with existing agricultural machinery and infrastructure. Furthermore, the use of servo motors enables the robot to navigate a variety of terrains and complex environments, broadening its applicability across diverse farming practices and landscapes. Through field testing and performance evaluation, we demonstrate the effectiveness of the robotic system in enhancing operational efficiency, reducing labor costs, and minimizing environmental impact. Future developments will focus on system optimization, integration of advanced sensing technologies, and real-world deployment to maximize its contribution to global food production.

AN INTERVAL-VALUED SPHERICAL FUZZY SWARA-CRADIS APPROACH TO STRATEGIC PROBLEM-SOLVING IN LOCAL MEDIA BUSINESSES

Aleyna SARIGÜL MERT, Ahmet AYTEKİN — Sun, 30 Nov 2025 12:54:50 +0100

This research aims to identify the key challenges faced by local media businesses, assess their severity, and propose strategic solutions. As social media and technological advancements continue to transform the media landscape, local media organizations are struggling with a wide range of problems. However, most existing strategies have failed to achieve their intended outcomes. The study employs a two-stage data collection process conducted in Artvin province, Turkey. In the first stage, the main challenges and potential strategic solutions were identified based on expert opinions. The problems of local media companies were categorized under the following dimensions: economic issues, technological and digital infrastructure, employment and skilled personnel shortages, structural and institutional challenges, legal and administrative barriers, content production and journalistic quality, distribution and accessibility, and media–political relations and ethical concerns. In the second stage, these problems and strategic solution proposals were evaluated based on experts’ assessments using the Interval-Valued Spherical Fuzzy SWARA-CRADIS methodology. The findings indicate that local media businesses struggle not only with limited economic resources but also with difficult working conditions, insufficient leave, excessive workloads, and the migration of qualified personnel. The proposed strategic solutions focus on strengthening legal and regulatory support, focusing on local community engagement, and enhancing accessibility and content diversity.

THE IMPACT OF DEMOGRAPHIC COMPOSITION IN UTKFACE AND APPA-REAL DATASETS ON FAIRNESS IN AGE ESTIMATION MODELS

Nenad PANIĆ — Sun, 07 Dec 2025 20:06:43 +0100

This paper analyzes the impact of demographic composition on fairness in facial age estimation models trained on the UTKFace and APPA-REAL datasets. Building on previously published empirical results, the study provides a theoretical and analytical interpretation of how dataset imbalance affects model bias. Through comparative evaluation of group-wise performance metrics including Mean Absolute Error, Standard Deviation, Disparate Impact, and Equality of Opportunity, the paper introduces the concept of a Distributional Fairness Baseline (DFB) as a diagnostic framework for separating dataset-driven bias from model-induced bias. The analysis reveals that fairness is primarily a function of the representativeness and internal structure of training data, rather than model architecture. Contrary to common assumptions, full data equalization through oversampling does not necessarily enhance equity and may even amplify disparities due to overfitting and redundancy. Instead, moderate redistribution, particularly controlled undersampling of dominant groups often achieves an optimal balance between accuracy and fairness. These findings emphasize that equitable model performance depends on both quantitative and qualitative diversity within datasets, establishing data design as the central determinant of fairness in automated age estimation systems.

PRIORITIZATION OF CRITERIA FOR PRODUCTION PLANNING SOFTWARE SELECTION USING PICTURE FUZZY PIPRECIA METHOD: A CASE OF THE ORDU PROVİNCE

Selçuk KORUCUK, Ahmet AYTEKİN — Mon, 08 Dec 2025 00:56:42 +0100

With technological transformation, businesses have begun to carry out more effective production planning and have increasingly needed production planning software programs for short-, medium-, and long-term planning activities. Research shows that production planning software provides significant benefits to businesses in various operational areas such as time management, workforce allocation, production scheduling, overtime control, and inventory management. In addition to enhancing operational efficiency, these software systems also contribute to reducing costs, using resources more effectively, and improving overall organizational performance. However, determining the criteria used in selecting the most suitable production planning software is crucial and requires careful consideration. Within the scope of this study, the criteria used in production planning software selection in manufacturing enterprises were identified and prioritized. For this purpose, the Picture Fuzzy PIPRECIA method was applied. According to the analysis results, among the criteria used in selecting production planning software in manufacturing enterprises, the most important criteria were identified as “Security” and “Reporting and Analysis,” while the least important criteria were found to be “Support and Training” and “Updating and Maintenance.

THE DEVELOPMENT SCOPE AND PERSPECTIVES OF SOCIAL BONDS AS AN INNOVATIVE INSTRUMENT FOR FINANCING SOCIAL IMPACT

Ana ANUFRIJEV, Anđelka ANIČIĆ, Almaz GIZIEW — Sun, 21 Dec 2025 21:51:46 +0100

The paper analyzes the development, functioning mechanisms and prospects of social bonds as an innovative financial instrument aimed at achieving measurable social impact. Social bonds are based on a results-based financing model, in which private capital is mobilized for the implementation of projects of public importance, while the return on investment is paid only if predefined social outcomes are achieved. The paper discusses the key characteristics of social bonds, their advantages and limitations, with an analysis of international experiences and the implementation of different models. Special emphasis is placed on institutional prerequisites, the quality of performance measurement, the distribution of risks between actors and the importance of transparent evaluation. Through a review of available case studies, examples of the application of social bonds in the areas of employment of vulnerable groups, education, social protection and public health are presented. The findings suggest that social bonds can contribute to more efficient and sustainable financing of social policies, but their success depends on the regulatory framework, institutional capacity and the quality of available data. The paper provides a basis for assessing the feasibility of applying this instrument in developing countries and provides guidelines for future research.

Keywords: Social bonds, innovative financial instruments, performance-based financing, social impact, public policies, sustainable financing, performance evaluation.

THE ROLE OF ARTIFICIAL INTELLIGENCE IN DECISION-MAKING AND INNOVATION IN PRODUCT DEVELOPMENT: A SYSTEMATIC LITERATURE REVIEW

Luka GLUŠČEVIĆ, Rajko IVANIŠEVIĆ — Sun, 21 Dec 2025 23:11:08 +0100

Artificial intelligence is changing how organizations develop products and make decisions. This literature review shows that AI is now a key driver for innovation and efficiency in product management. Companies use AI tools to improve every stage of the product lifecycle, from idea creation to final delivery and ongoing updates. AI helps managers analyze large sets of data, predict market trends, and speed up decision processes. Instead of replacing people, AI often supports human work by allowing teams to solve complex problems and test new ideas faster. However, successful AI adoption depends on quality data, organizational readiness, and clear strategies. Main challenges include technical questions, data trust, ethical issues, and staff training. Best practices highlight the importance of combining human expertise with AI tools, using agile methods, and developing transparent, responsible systems. Research gaps remain in understanding AI’s long-term effects, especially in non-digital sectors and on employee motivation. This review provides a structured overview of trends, challenges, and future research directions for AI in product management and decision-making.

FACTORS INFLUENCING INDIVIDUAL SAVING BEHAVIOR: A LITERATURE REVIEW

Shine EMENIDO — Sun, 21 Dec 2025 23:33:21 +0100

Saving is crucial for financial stability and economic growth. However, many struggles to balance saving and spending due to low financial literacy and insufficient income. This study examined the factors that influence saving behavior of individuals in the Philippines to address barriers to effective saving habits. Specifically, this research aims to fill the gap in identifying the factors influencing saving behavior among Filipinos. Using a qualitative methodology, the study systematically reviewed and compared prior literature's methodologies, objectives, and findings, to identify significant and common factors influencing saving habits. The results showed the factors influencing saving behavior are as follows: parental socialization, financial literacy, self-control, and peer influence; sociodemographic factors including education, income and gender, family background, attitude, financial literacy, and locality, financial attitude toward saving and self-efficacy. Furthermore, this research may help address issues that result in Filipinos not having enough income to set aside savings. In conclusion, this study emphasizes the importance of saving as it can impact a nation's growth by contributing to capital accumulation, financial resilience, and economic stability, driving long-term growth, and reducing the vulnerability of the Philippine economy to external shocks.