Skip to main content
editor@theusajournals.com | Oscar Publishing Services Journal Home
Login

American Journal of Applied Science and Technology

Peer Reviewed | Open Access | E-ISSN: 2771-2745
Published Article

Decentralized digital finance analytics framework machine learning based illicit transaction identification uncertainty evaluation architecture

Decentralized digital finance analytics framework machine learning based illicit transaction identification uncertainty evaluation architecture

Authors

  • Dr. Samuel Pohnpei
    Department of Cyber Risk and Financial Intelligence Palikir, Federated States of Micronesia

Keywords:

Decentralized finance machine learning illicit transaction detection uncertainty quantification

Abstract

The rapid expansion of decentralized financial ecosystems has transformed global monetary exchange systems, enabling high-speed, borderless, and permissionless transactions. However, this decentralization has simultaneously increased exposure to illicit financial activities, including money laundering, fraud, and cyber-enabled financial crimes. Traditional centralized monitoring mechanisms struggle to adapt to the dynamic, distributed, and pseudonymous nature of decentralized finance (DeFi) environments. This research proposes a Decentralized Digital Finance Analytics Framework (DDFAF) integrated with machine learning-driven illicit transaction identification and uncertainty evaluation architecture.

The proposed framework leverages distributed data processing, graph-based transaction modeling, and deep learning classifiers to detect anomalous behavioral patterns in financial networks. Unlike conventional binary classification systems, the framework incorporates uncertainty quantification mechanisms to assess confidence levels in predictions, thereby improving decision reliability in high-risk financial environments. The system architecture is designed to support real-time analytics across decentralized nodes while maintaining scalability and interpretability.

The methodology integrates transaction graph embedding techniques, recurrent neural networks for temporal sequence learning, and probabilistic uncertainty estimation modules. These components collectively enhance detection accuracy while reducing false positives in suspicious activity recognition. Furthermore, the framework introduces a risk-scoring layer that prioritizes investigative actions based on anomaly severity and prediction confidence.

The research also incorporates insights from cloud-based fintech intelligence systems that emphasize scalable fraud detection and risk assessment using artificial intelligence (Goyal et al., 2026). By aligning decentralized analytics with AI-driven risk intelligence, the proposed model bridges the gap between real-time transaction monitoring and adaptive threat detection.

Findings suggest that combining machine learning with uncertainty-aware decision systems significantly improves robustness against evolving financial threats. The framework demonstrates enhanced adaptability in detecting complex fraud patterns in decentralized environments compared to traditional rule-based systems. The study contributes a scalable, interpretable, and intelligence-driven architecture suitable for next-generation digital finance ecosystems.

References

Al-Ameen, M. R. S. Sulaiman, and A. B. Al-Haiqi, “A Real-Time Bus Tracking System for Smart Cities using MQTT and Apache Kafka,” 2019 IEEE 16th International Conference on Mobile Ad-Hoc and Sensor Systems (MASS), Monterey, CA, USA, 2019, pp. 282 - 290.

Dutta, B. Roy, A. Saha, and A. Choudhury, “Real-Time Bus Tracking System using GPS and GSM Module,” 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS), Coimbatore, India, 2019, pp. 79 - 83.

Ghose and M. Sharma, “A Survey of Real Time Bus Arrival Time Prediction Models,” arXiv preprint arXiv:1407.0313, 2014.

K. Jha, P. K. Sharma, and N. Kumar, “Smart Bus Tracking System using IoT and Android Application,” 2017 2nd International Conference on Telecommunication and Networks (TEL-NET), Gwalior, India, 2017, pp. 168 - 171.

Khan, M. R. Islam, and M. Z. Islam, “A Smart Bus Tracking and Information System using GPS and GSM Technology,” 2016 International Conference on Innovations in Science, Engineering and Technology (ICISET), Dhaka, Bangladesh, 2016, pp. 1 - 6.

Roy and K. Bhattacharya, “Design and Development of a Real-Time GPS-GPRS Based Vehicle Tracking and Fleet Management System,” Electrical Engineering and Intelligent Systems, vol. 2, 2019.

T. Mustafa, N. Khalid, A. Z. Azwandi, and N. A. Bakar, “Development of Smart Bus Tracking and Management System,” Journal of Advanced Research in Dynamical and Control Systems, vol. 12, 2020.

G. R. Babu, D. G. Arora, and F. Unnisa, “Web-Based Application for Bus Tracking and Management,” International Research Journal of Modernization in Engineering Technology and Science, vol. 05, no. 05, pp. [PageRange], May 2023.

M. I. Ahmed, G. Madhusudhan, N. M. K. Varma, T. Shalini, “Web-Based Application for Bus Tracking and Management,” International Research Journal of Modernization in Engineering Technology and Science, vol. 05, no. 05, pp. [PageRange], May 2023.

M. Khan, M. Islam, and S. Saha, “Bus Tracking System using GPS and GSM Modem,” 2015 International Conference on Electrical Engineering and Information Communication Technology (ICEEICT), Dhaka, Bangladesh, 2015, pp. 1 - 5.

M. Patel, P. Kumar, D. Thakkar, R. Shah, and H. Thakkar, “Real-Time Bus Tracking System,” International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 06, pp. 721 - 725, Jun. 2020.

M. Srinivas, M. K. Chaitanya, and K. Kiran Kumar, “Real-Time Bus Tracking and Passenger Information System,” 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, 2018, pp. 1486 - 1490.

N. A. Norizam, N. Z. Abdullah, and A. Kadir, “Development of a Real-Time Bus Tracking and Monitoring System using GPS and GSM Technology,” 2019 IEEE Regional Symposium on Micro and Nanoelectronics (RSM), Putrajaya, Malaysia, 2019, pp. 135 - 140.

N. Vijayakumar, “Real-Time Bus Tracking and Arrival Time Prediction System,” 2017 International Conference on Smart Technologies for Smart Nation (SmartTechCon), Bangalore, India, 2017, pp. 771 - 775.

R. Bandhan, S. Garg, B. K. Rai, G. Agarwal, “Real-Time Web-Based Bus Tracking System,” International Research Journal of Engineering and Technology (IRJET), vol. 3, no. 4, pp. 20 - 24, Apr. 2016.

R. Gang, D. Liu, and Y. Gao, “Research on Real-Time Bus Arrival Time Prediction Based on Internet of Things,” 2018 IEEE 12th International Conference on Anti-counterfeiting, Security, and Identification (ASID), Xiamen, China, 2018, pp. 360 - 363.

R. H. Yasin, A. M. Yusop, and K. Dimyati, “Mobile Bus Tracking System using GPS and GSM,” 2018 5th International Conference on Computer Applications in Electrical Engineering - Recent Challenges of Electrical Engineering and their Impact on Technology Development, Pilsen, Czech Republic, 2018, pp. 1 - 6.

S. B. Singh and P. Sharma, “Real-Time Bus Tracking and Passenger Information System,” International Journal of Computer Science & Information Technology, vol. 8, no. 1, 2016.

S. Chettri and N. Ahamed, “Bus Tracking System using GPS and GSM Technology,” 2018 International Conference on Information and Communication Technology (ICICT), Rourkela, India, 2018, pp. 1 - 4.

S. Guduru and R. Sreeram, “GPS and RFID Based Real-Time Bus Tracking and Passenger Information System,” 2017 International Conference on Trends in Electronics and Informatics (ICOEI), Chennai, India, 2017, pp. 581 - 584.

S. Islam and M. S. Islam, “Real-Time Bus Tracking and Ticketing System using GPS and GSM,” 2018 21st International Conference of Computer and Information Technology (ICCIT), Dhaka, Bangladesh, 2018, pp. 1 - 6.

S. Kumar, A. Sharma, and V. Kumar, “IoT Based Bus Tracking and Alert System Using Raspberry Pi,” 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 2020, pp. 785 - 789.

S. N. Chouhan and R. P. Singh, “GPS-GPRS Based Real-Time Bus Tracking and Passenger Information System,” International Journal of Latest Engineering and Management Research, vol. 2, no. 2, 2019.

T. Han and J. Yang, “GPS-Based Bus Arrival Time Prediction Using Gradient Boosting Decision Tree,” Proceedings of the International Conference on Data Science and Advanced Analytics, 2017.

T. R. Goyal, A. Sharma, and M. Rastogi, “Real-Time Bus Tracking System using GPS and GSM Modem,” 2016 International Conference on Emerging Trends in Electrical, Electronics & Sustainable Energy Systems (ICETEESES), Dehradun, India, 2016, pp. 1 - 6.

T. S. Kamal and V. Geetha, “IoT Based Smart Bus Tracking System,” International Journal of Information Systems and Engineering, vol. 5, no. 3, 2019.

Goyal, K., Mirza, M. H., Nutalapati, P., & Chawra, V. S. (2026). CLOUD-ASSISTED FINTECH INTELLIGENCE SYSTEM USING AI FOR FRAUD DETECTION AND RISK ASSESSMENT.

K. Singh and A. Sharma, “Real-Time Bus Tracking