AI-Driven Algorithmic Intelligence for Navigating Complexity: Entropy-Based Models for Cybercrime and Management Economic and Financial Systems

Bekim Fetaji; Fati Iseni; Miki Runtev; Pavle Trpeski; Gjorgi Slamkov; Hristina Serafimovska; Majlinda Fetaji

doi:10.23947/2334-8496-2026-14-2-231-246

Authors

Bekim Fetaji Mother Teresa University, UMT Faculty of Informatics, MTU campus, Skopje, Republic of North Macedonia https://orcid.org/0000-0001-9578-9443
Fati Iseni Mother Teresa University, UMT Faculty of Informatics, MTU campus, Skopje, Republic of North Macedonia https://orcid.org/0000-0001-6160-5298
Miki Runtev European University Skopje, Faculty of Economy, Bul. Saint Clement Ohridski, Republic of North Macedonia https://orcid.org/0009-0003-1998-4214
Pavle Trpeski European University Skopje, Faculty of Economy, Bul. Saint Clement Ohridski, Republic of North Macedonia https://orcid.org/0000-0002-9703-392X
Gjorgi Slamkov University Goce Delcev, Faculty of Law, Stip 1200, North Macedonia https://orcid.org/0009-0005-2647-9616
Hristina Serafimovska University Goce Delcev, Faculty of Tourism and Business Logistics, Štip, North Macedonia https://orcid.org/0000-0003-2264-6411
Majlinda Fetaji South East European University, CST Faculty, SEEU campus, Tetovo, Republic of North Macedonia https://orcid.org/0009-0001-5457-5032

DOI:

https://doi.org/10.23947/2334-8496-2026-14-2-231-246

Keywords:

AI, Data-Driven history, Algorithmic Intelligence, Entropy-Based, Cybercrime, Economic and Financial Management Systems

Abstract

Navigating the complexities of modern organizational landscapes, particularly in the context of cybercrime and economic – financial challenges, remains a critical issue for industries. Despite advancements in hybrid intelligence, cloud-based platforms, and algorithmic solutions, gaps persist in integrating data-driven, entropy-based approaches into next-generation management systems tailored for cybercrime prevention and economic optimization. This study addresses these gaps by proposing a novel framework that integrates a hybrid algorithmic model with entropy-based optimization techniques. Utilizing four datasets—three publicly available and one originally collected through online sources—this research explores how real-time data and adaptive decision-making can enhance cybercrime detection and economic – financial forecasting. The theoretical novelty lies in combining entropy-based modeling with a rule-based neural network to achieve superior accuracy, explainability, and scalability in complex settings. The proposed system delivers practical benefits, including improved cyberthreat identification, economic anomaly detection, and resource optimization, fostering resilient and adaptive management frameworks. Experimental results demonstrate statistically significant improvements in accuracy (p < 0.05) compared to baseline models, particularly in dynamic, resource-intensive environments. This study contributes to the literature by offering a comprehensive empirical evaluation, discussing integration with existing enterprise systems, and addressing scalability and cost-effectiveness in the context of cybercrime and economic management. By bridging these research gaps, we present an approach with both theoretical significance and practical utility for combating cybercrime and optimizing economic and financial performance.

Downloads

Download data is not yet available.

👁 Abstract Views: 0📥 PDF Downloads: 0

References

Altintas, I., Block, J., Crawl, DL., Callafon, RAd. (2023). Using Dynamic Data-Driven Cyberinfrastructure for Next-Generation Wildland Fire Intelligence. Handbook of Dynamic Data Driven Applications Systems, 451-474. https://doi.org/10.1007/978-3-031-27986-7_17

Aslam, A., Qureshi, KN., Hussain, A. (2024). Advanced AI-Based Healthcare Systems Applications and Services. Next Generation AI Language Models in Research, 86-113. https://doi.org/10.1201/9781032667911-4

Brunner, D., Legat, C., Seebacher, U. (2024). Towards Next Generation Data-Driven Management. Collective Intelligence, 152-203. https://doi.org/10.1201/9781032690711-8

Erkunt, H. (2023). Empowering the Next Generation: Integrating AI Literacy into Modern Education. Cognitive Models and Artificial Intelligence Conference Proceedings, 33-35. https://doi.org/10.36287/setsci.6.1.014

Jain, P., Tripathi, V., Malladi, R., Khang, A. (2023). Data-Driven Artificial Intelligence (AI) Models in the Workforce Development Planning. Designing Workforce Management Systems for Industry 4.0, 159-176. https://doi.org/10.1201/9781003357070-10

Jha, R. (2024). Navigating risk complexity associated with data philanthropy for AI. The Routledge Handbook of Artificial Intelligence and Philanthropy, 309-327. https://doi.org/10.4324/9781003468615-23

Khatoon, A., Ullah, A., Qureshi, KN. (2024). AI Models and Data Analytics. Next Generation AI Language Models in Research, 45-85. https://doi.org/10.1201/9781032667911-3

Kopitar, L., Kocbek, P., Gosak, L., Stiglic, G. (2025). Review of data-driven generative AI models for knowledge extraction from scientific literature in healthcare. Next Generation eHealth, 127-146. https://doi.org/10.1016/b978-0-443-13619-1.00007-6

Kumar, BSS., Moitessier, A., Moitessier, N. (2025). Toxicity Forecasts: Navigating Data-Driven AI/ML Models: From Theory to Practice. Artificial Intelligence for Chemical Sciences, 209-246. https://doi.org/10.1201/9781003569282-11

Losavio, MM. (2023). Legal Issues with AI/Algorithmic Systems. Concepts in Smart Societies, 107-121. https://doi.org/10.1201/9781003251507-7

Mitra, U., Rehman, SU. (2024). Leveraging AI and Machine Learning for Next-Generation Clinical Decision Support Systems (CDSS). Advances in Healthcare Information Systems and Administration, 83-112. https://doi.org/10.4018/979-8-3693-7277-7.ch003

Mohanty, A., Raghavendra, GS., Rajini, J., Sachuthananthan, B., Banu, EA., Subhi, B. (2024). Artificial Intelligence (AI) and Machine Learning (ML) Technology-Driven Structural Systems. Advances in Systems Analysis, Software Engineering, and High Performance Computing, 225-254. https://doi.org/10.4018/979-8-3693-0968-1.ch009

Noran, O., Bernus, P., Caluianu, S. (2020). Situation-aware Building Information Models for Next Generation Building Management Systems. Proceedings of the 22nd International Conference on Enterprise Information Systems, 75-82. https://doi.org/10.5220/0008767900750082

Ozurumba, E., Eboh, IP. (2024). Leveraging AI-Driven Decision Intelligence for Systems Engineering Complexity. International Journal of Research Publication and Reviews 5(11), 4374-4389. https://doi.org/10.55248/gengpi.5.1124.3318

Pascual-Reguant, A. (2024). Review for Towards the Next Generation of Data-Driven Therapeutics Using Spatially Resolved Single-Cell Technologies and Generative AI. https://doi.org/10.1002/eji.202451234/v1/review2

Piller, FT., Nitsch, V., Aalst, Wvd. (2022). Hybrid Intelligence in Next Generation Manufacturing: An Outlook on New Forms of Collaboration Between Human and Algorithmic Decision-Makers in the Factory of the Future. Contributions to Management Science, 139-158. https://doi.org/10.1007/978-3-031-07734-0_10

Pütz, S., Dyck, MV., Lüttgens, D., Mertens, A. (2022). Big Picture of Next Generation Manufacturing. Contributions to Management Science, 43-53. https://doi.org/10.1007/978-3-031-07734-0_3

Qudrat-Ullah, H. (2025). Integrating Systems Thinking and AI. Navigating Complexity, 39-68. https://doi.org/10.1007/978-3-031-82742-6_3

Raghav, YY., Vyas, V. (2024). Leveraging cloud computing for efficient AI-based data-driven systems. Artificial Intelligence and Internet of Things based Augmented Trends for Data Driven Systems, 55-70. https://doi.org/10.1201/9781003497318-4

Raju, P., Arun, R., Turlapati, VR., Veeran, L., Rajesh, S. (2024). Next-Generation Management on Exploring AI-Driven Decision Support in Business. Advances in Computational Intelligence and Robotics, 61-78. https://doi.org/10.4018/979-8-3693-8659-0.ch004

Saadat, S. (2023). Data-Driven Coexistence in Next-Generation Heterogeneous Cellular Networks. Data-Driven Intelligence in Wireless Networks, 213-236. https://doi.org/10.1201/9781003216971-12

Sarmas, E., Stamatopoulos, S., Kapsalis, P., Touloumis, K., Marinakis, V. (2023). A Next Generation Library of AI-Based Data-Driven Services for the Built Environment. 2023 14th International Conference on Information, Intelligence, Systems & Applications (IISA), 1-8. https://doi.org/10.1109/iisa59645.2023.10345945

Schollemann, A., Wiesch, M., Brecher, C., Schuh, G. (2022). Resilience Drivers in Next Generation Manufacturing. Contributions to Management Science, 119-128. https://doi.org/10.1007/978-3-031-07734-0_8

Shah, C., Sabbella, VRR., Buvvaji, HV. (2024). From Deterministic to Data-Driven: AI and Machine Learning for Next-Generation Production Line Optimization. Journal of Artificial Intelligence and Big Data 2(1), 21-31. https://doi.org/10.31586/jaibd.2022.952

Webb, S. (2025). Review for Towards the Next Generation of Data-Driven Therapeutics Using Spatially Resolved Single-Cell Technologies and Generative AI. https://doi.org/10.1002/eji.202451234/v2/review1

Whig, P., Venkata, S., Bhatia, AB. (2024). Cloud computing in AI-based data-driven systems. Artificial Intelligence and Internet of Things based Augmented Trends for Data Driven Systems, 16-34. https://doi.org/10.1201/9781003497318-2

Xue, Z., Zheng, Y. (2024). RB-Net: Rule-Based Neural Networks with Interpretable Models. 2024 Sixth International Conference on Next Generation Data-driven Networks (NGDN), 64-68. https://doi.org/10.1109/ngdn61651.2024.10744176

List of Figures

Figure 1. High-Level System Architecture

A schematic illustrating the multi-layered data flow, including input streams, rule-based neural network (RBNN) processing, an entropy-based decision module (EBDM), and final outputs. Annotations highlight data rates, entropy thresholds, and cloud integration points.

Figure 2. Entropy-Based Data Flow

A flowchart demonstrating how raw data is routed through the EBDM. Includes numerical annotations of sample entropy values (ranging from 0.1 to 0.9) correlated with data complexity.

Figure 3. Model Accuracy vs. Training Epochs

A line plot comparing the performance of the Random Forest (RF), Feedforward Neural Network (FNN), and the proposed RBNN + EBDM over 50 training epochs. Key epochs are labeled to indicate accuracy trends.

Figure 4. Execution Time vs. Data Size

A bar chart showing how execution time scales for each model (RF, FNN, and RBNN + EBDM) as data volume increases (e.g., from 500MB to 1.5GB). Numerical labels identify exact running times in seconds.

Figure 5. Scalability Analysis Bar Chart

A comparative bar chart illustrating accuracy and F1-score at incremental data size increases (+20%, +40%, +60%). Displays the resilience of RBNN + EBDM in maintaining high performance levels.

List of Tables

Table 1. Comparative Overview of the Four Datasets

Summarizes the primary characteristics of each dataset, including record count, number of features, domain type, and approximate data volume. Highlights the diversity of inputs, especially the novel Dataset D.

Table 2. Data Preprocessing Steps Applied to All Datasets

Provides a concise description of missing-value imputation, outlier detection, categorical encoding, and normalization techniques used uniformly across all four datasets.

Table 3. Statistical Summary of Model Results (Accuracy, F1-Score, EC)

Shows comparative performance metrics for three models—Random Forest, Feedforward Neural Network, and the proposed RBNN + EBDM—across multiple datasets. The custom entropy-confidence (EC) metric is introduced to assess interpretability.

Table 4. Comparative Performance of Baseline vs Proposed Model

Illustrates the execution time and memory usage for each model under different data sizes. Demonstrates how the proposed RBNN + EBDM scales compared to baseline approaches.

Table 5. Scalability Analysis under Increasing Data Volume

Examines accuracy and F1-score changes when datasets are expanded by various increments (+20%, +40%, +60%). Highlights the robust performance retention of the proposed model in large-scale environments.