Oana-Alexandra Dragomirescu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Oana-Alexandra Dragomirescu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Ana-Ramona Bologa
Department of Economic Informatics and Cybernetics, Bucharest University of Economic Studies, 15-17 Dorobanti Avenue, District 1, 010552 Bucharest, Romania
3 shared publications - Pavel-Cristian Craciun
The Bucharest University of Economic Studies , Bucharest , Romania
2 shared publications Andreea-Izabela Bostan
Bucharest University of Economic Studies
1 shared publication- Andreea-Maria Trăistaru
Independent Researcher, 010374 Bucharest, Romania
1 shared publication - George Eduard Grigore
National University of Science and Technology POLITEHNICA Bucharest , Bucharest , Romania
1 shared publication - Oana-Larisa Stoica
Bucharest University of Economic Studies , Bucharest , Romania
1 shared publication
Latest Publications
- Open Access
- 1 July 2026
- Published by Walter de Gruyter GmbH in Proceedings of the International Conference on Business Excellence
- Vol. 20 (1) , 595-609
An RPA- and OCR-Based Approach towards Smarter Expense Management
At the moment, the corporate sector is still actively being dominated by manual expense management processes. This in turn continues to lead to numerous inefficient workflows, generally increased administrative costs and on average, to a higher-than-acceptable likelihood of data-entry errors. This paper proposes an automated expense management system which uses Optical Character Recognition (OCR) and Robotic Process Automation (RPA) technologies for efficient processing of financial documents. The proposed solution was evaluated on a dataset of 120 documents representative of common categories of organisational expenses. Experiments demonstrate that the system can reduce the average processing time of an expense report from 10 to 15 minutes to only 2 to 4 minutes, i.e., by about 70-80%. The OCR module had an average data extraction accuracy of approximately 93% across various document types. The results show that the combination of intelligent document processing and workflow automation can improve the efficiency, accuracy and compliance of organisational expense management systems substantially.
- 1 July 2026
- Published by Walter de Gruyter GmbH in Proceedings of the International Conference on Business Excellence
- Vol. 20 (1) , 595-609
Open AccessAn RPA- and OCR-Based Approach towards Smarter Expense Management
At the moment, the corporate sector is still actively being dominated by manual expense management processes. This in turn continues to lead to numerous inefficient workflows, generally increased administrative costs and on average, to a higher-than-acceptable likelihood of data-entry errors. This paper proposes an automated expense management system which uses Optical Character Recognition (OCR) and Robotic Process Automation (RPA) technologies for efficient processing of financial documents. The proposed solution was evaluated on a dataset of 120 documents representative of common categories of organisational expenses. Experiments demonstrate that the system can reduce the average processing time of an expense report from 10 to 15 minutes to only 2 to 4 minutes, i.e., by about 70-80%. The OCR module had an average data extraction accuracy of approximately 93% across various document types. The results show that the combination of intelligent document processing and workflow automation can improve the efficiency, accuracy and compliance of organisational expense management systems substantially.
- Open Access
Adaptive Financial Infrastructure: A DevOps–Machine Learning Framework for Predictive Resource and Operational Optimization
Financial systems operate under strict requirements for availability, low latency, resilience, and regulatory compliance, yet infrastructure management in these environments remains largely reactive. This paper addresses that limitation by proposing a DevOps–Machine Learning framework for predictive resource and operational optimization in adaptive financial infrastructure. The study follows an artefact-oriented approach inspired by Design Science Research: the framework is defined conceptually, instantiated as a containerized Proof of Concept, and evaluated through controlled benchmarking. The proposed architecture integrates observability, workload forecasting, decision support, and automated actuation to support proactive scaling and more adaptive operational control in cloud-based financial environments. The experimental setup uses synthetic financial-like workloads with cyclical demand, stochastic variation, and sudden spikes to compare conventional reactive scaling with forecast-enhanced strategies. The results indicate that embedding predictive intelligence into infrastructure operations improves the ability to anticipate workload changes and offers a more structured basis for balancing responsiveness, operational control, and resource efficiency than purely threshold-based mechanisms. The study concludes that predictive resource and operational optimization in financial systems should not be treated as an isolated autoscaling problem, but as part of a broader DevOps–Machine Learning architecture for adaptive financial infrastructure.
Open AccessAdaptive Financial Infrastructure: A DevOps–Machine Learning Framework for Predictive Resource and Operational Optimization
Financial systems operate under strict requirements for availability, low latency, resilience, and regulatory compliance, yet infrastructure management in these environments remains largely reactive. This paper addresses that limitation by proposing a DevOps–Machine Learning framework for predictive resource and operational optimization in adaptive financial infrastructure. The study follows an artefact-oriented approach inspired by Design Science Research: the framework is defined conceptually, instantiated as a containerized Proof of Concept, and evaluated through controlled benchmarking. The proposed architecture integrates observability, workload forecasting, decision support, and automated actuation to support proactive scaling and more adaptive operational control in cloud-based financial environments. The experimental setup uses synthetic financial-like workloads with cyclical demand, stochastic variation, and sudden spikes to compare conventional reactive scaling with forecast-enhanced strategies. The results indicate that embedding predictive intelligence into infrastructure operations improves the ability to anticipate workload changes and offers a more structured basis for balancing responsiveness, operational control, and resource efficiency than purely threshold-based mechanisms. The study concludes that predictive resource and operational optimization in financial systems should not be treated as an isolated autoscaling problem, but as part of a broader DevOps–Machine Learning architecture for adaptive financial infrastructure.
- Open Access
- 1 February 2026
- Published by MDPI AG in Information
- Vol. 17 (2) , 132
The Nexus Between Digital Finance, Automation, Environmental, Social, and Governance (ESG) Objectives: Evidence Based on a Bibliometric Analysis
The main purpose of this study was to conduct a bibliometric analysis of scientific knowledge and trends in modern finance. To this end, the analysis was based on the keywords: “finance”, “automation”, and “ESG”. The analysis aimed to provide theoretical insights into the economic and financial implications of automation and its role in achieving ESG objectives. From a methodological standpoint, bibliometric research was conducted on 21 September 2025. It involved analysing a total of 16,500 scientific articles published between 1974 and 2026 in two databases: The Web of Science Core Collection and Scopus. The Bibliometrix R 5.2.0 version tool was used to generate visualisations. Thematic mapping, three-field plotting, keyword mapping, and clustering were the main methods used to analyse the associations between finance, automation, and ESG principles. The study’s results showed an average annual increase in publications of approximately 3.80% and 2.50%, respectively, while international collaborations between researchers have become increasingly prominent in recent years. At the same time, the co-occurrence network analysis identified five key thematic clusters in the Web of Science Core Collection and three in Scopus. From a comparative perspective, these clusters highlight the most significant connections between environmental, social, and governance (ESG) performance, corporate social responsibility (CSR) impact, financial performance, economic growth, sustainable development, and the implications of the automation process. From a bibliometric point of view, this research contributes to a better understanding of the multiple digital transformations specific to the current financial framework, generating possible future research directions on the significant role of automation in financial, environmental, and social performance. Furthermore, automation is a critical component of the digital future of finance. Analysing and investigating the causal relationships between automation and Environmental, Social, and Governance (ESG) principles will necessitate new areas of study within the financial sphere.
- 1 February 2026
- Published by MDPI AG in Information
- Vol. 17 (2) , 132
Open AccessThe Nexus Between Digital Finance, Automation, Environmental, Social, and Governance (ESG) Objectives: Evidence Based on a Bibliometric Analysis
The main purpose of this study was to conduct a bibliometric analysis of scientific knowledge and trends in modern finance. To this end, the analysis was based on the keywords: “finance”, “automation”, and “ESG”. The analysis aimed to provide theoretical insights into the economic and financial implications of automation and its role in achieving ESG objectives. From a methodological standpoint, bibliometric research was conducted on 21 September 2025. It involved analysing a total of 16,500 scientific articles published between 1974 and 2026 in two databases: The Web of Science Core Collection and Scopus. The Bibliometrix R 5.2.0 version tool was used to generate visualisations. Thematic mapping, three-field plotting, keyword mapping, and clustering were the main methods used to analyse the associations between finance, automation, and ESG principles. The study’s results showed an average annual increase in publications of approximately 3.80% and 2.50%, respectively, while international collaborations between researchers have become increasingly prominent in recent years. At the same time, the co-occurrence network analysis identified five key thematic clusters in the Web of Science Core Collection and three in Scopus. From a comparative perspective, these clusters highlight the most significant connections between environmental, social, and governance (ESG) performance, corporate social responsibility (CSR) impact, financial performance, economic growth, sustainable development, and the implications of the automation process. From a bibliometric point of view, this research contributes to a better understanding of the multiple digital transformations specific to the current financial framework, generating possible future research directions on the significant role of automation in financial, environmental, and social performance. Furthermore, automation is a critical component of the digital future of finance. Analysing and investigating the causal relationships between automation and Environmental, Social, and Governance (ESG) principles will necessitate new areas of study within the financial sphere.
- Open Access
- 1 July 2025
- Published by Walter de Gruyter GmbH in Proceedings of the International Conference on Business Excellence
- Vol. 19 (1) , 1260-1281
Contributions on Automating the Financial Dunning Process Using Machine Learning
Dunning refers to the process of methodically pursuing payment of a debt. The practice of dunning has been around for centuries, but technological developments, especially in Machine Learning (ML), present a chance to automate and optimize important processes, increasing recovery rates and improving customer satisfaction. The research’s objectives were to learn more about the difficulties arising from the dunning process’s lack of automation through machine learning (ML) and to create a solution that effectively automates the financial process by incorporating ML. To determine the primary obstacles, inefficiencies, and places in the dunning process that are best suited for automation, this article first offers a survey and a review of the literature. It provides a better grasp of how businesses currently manage dunning and the issues that impede productivity by examining industry data and professional viewpoints. The paper expands on these discoveries by offering a specific machine learning-driven automation solution intended to optimize the dunning procedure. By using predictive analytics to improve client segmentation, optimize communication scheduling, and predict payment patterns, this strategy eventually improves operational effectiveness and financial results. The essay illustrates how intelligent automation may make the dunning process a more efficient and data-driven function by bridging the gap between theory and reality.
- 1 July 2025
- Published by Walter de Gruyter GmbH in Proceedings of the International Conference on Business Excellence
- Vol. 19 (1) , 1260-1281
Open AccessContributions on Automating the Financial Dunning Process Using Machine Learning
Dunning refers to the process of methodically pursuing payment of a debt. The practice of dunning has been around for centuries, but technological developments, especially in Machine Learning (ML), present a chance to automate and optimize important processes, increasing recovery rates and improving customer satisfaction. The research’s objectives were to learn more about the difficulties arising from the dunning process’s lack of automation through machine learning (ML) and to create a solution that effectively automates the financial process by incorporating ML. To determine the primary obstacles, inefficiencies, and places in the dunning process that are best suited for automation, this article first offers a survey and a review of the literature. It provides a better grasp of how businesses currently manage dunning and the issues that impede productivity by examining industry data and professional viewpoints. The paper expands on these discoveries by offering a specific machine learning-driven automation solution intended to optimize the dunning procedure. By using predictive analytics to improve client segmentation, optimize communication scheduling, and predict payment patterns, this strategy eventually improves operational effectiveness and financial results. The essay illustrates how intelligent automation may make the dunning process a more efficient and data-driven function by bridging the gap between theory and reality.
- Open Access
Enhancing Invoice Processing Automation Through the Integration of DevOps Methodologies and Machine Learning
In today’s rapidly evolving digital landscape, organizations are increasingly seeking systemic approaches to optimize their financial operations, particularly in invoice processing. Traditional methods of invoice management, which are heavily reliant on manual labor, not only incur significant costs but also contribute to inefficiencies, delays, and resource wastage. This article presents an integrated framework that combines DevOps methodologies and machine learning (ML) to transform invoice processing into a scalable and sustainable operation. By leveraging system dynamics and automation, the proposed Proof of Concept (PoC) addresses interconnected challenges, such as reducing labor dependency, enhancing operational intelligence, and minimizing environmental impact. The PoC framework includes dynamic model training, testing, deployment, and monitoring, enabling adaptive and resilient solutions aligned with evolving business needs. Findings from a survey highlight the potential of these integrated approaches to streamline processes, reduce errors, and optimize resource utilization while also identifying barriers to widespread adoption. By combining ML’s predictive power with DevOps’ agility, the framework not only advances automation but also provides a path toward sustainable financial operations in an interconnected and data-driven economy.
Open AccessEnhancing Invoice Processing Automation Through the Integration of DevOps Methodologies and Machine Learning
In today’s rapidly evolving digital landscape, organizations are increasingly seeking systemic approaches to optimize their financial operations, particularly in invoice processing. Traditional methods of invoice management, which are heavily reliant on manual labor, not only incur significant costs but also contribute to inefficiencies, delays, and resource wastage. This article presents an integrated framework that combines DevOps methodologies and machine learning (ML) to transform invoice processing into a scalable and sustainable operation. By leveraging system dynamics and automation, the proposed Proof of Concept (PoC) addresses interconnected challenges, such as reducing labor dependency, enhancing operational intelligence, and minimizing environmental impact. The PoC framework includes dynamic model training, testing, deployment, and monitoring, enabling adaptive and resilient solutions aligned with evolving business needs. Findings from a survey highlight the potential of these integrated approaches to streamline processes, reduce errors, and optimize resource utilization while also identifying barriers to widespread adoption. By combining ML’s predictive power with DevOps’ agility, the framework not only advances automation but also provides a path toward sustainable financial operations in an interconnected and data-driven economy.
- 3 February 2024
- Published by Springer Nature
- p. 107-119
The Use of Blockchain Technology for Managing a Voting Process
- 3 February 2024
- Published by Springer Nature
- p. 107-119
The Use of Blockchain Technology for Managing a Voting Process