Milica Ciric

Ms. Milica Ciric

Department for Mathematics Physics and Informatics, Faculty of civil engineering and architecture, Niš, Serbia
orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 June 2023 in Electronics
Verified
Journal Article
Open access
PDF file
MCMilica Ciric
Milica Ciric
BPBratislav Predic
Bratislav Predic
DSDragan Stojanović
Dragan Stojanović
Ivan Toplica CiricIvan Toplica Ciric
Ivan Toplica Ciric
Data concerning product sales are a popular topic in time series forecasting due to their multidimensionality and wide presence in many businesses. This paper describes the research in predicting the timing and product category of the next purchase based on historical customer transaction data. Given that the dataset was acquired from a vendor of medical drugs and devices, the generic product identifier (GPI) classification system was incorporated in assigning product categories. The models built are based on recurrent neural networks (RNN) and long short-term memory (LSTM) neural networks with different input and output features, and training datasets. Experiments with various datasets were conducted and optimal network structures and types for predicting both product category and next purchase day were identified. The key contribution of this research is the process of data transformation from its original purchase transaction format into a time series of input features for next purchase prediction. With this approach, it is possible to implement a dedicated personalized marketing system for a vendor.

2 November 2023 in Electronics
Verified
Journal Article
Open access
PDF file
BPBratislav Predic
Bratislav Predic
MCMilica Ciric
Milica Ciric
LSLeonid Stoimenov
Leonid Stoimenov
The black-box nature of neural networks is an obstacle to the adoption of systems based on them, mainly due to a lack of understanding and trust by end users. Providing explanations of the model’s predictions should increase trust in the system and make peculiar decisions easier to examine. In this paper, an architecture of a machine learning time series prediction system for business purchase prediction based on neural networks and enhanced with Explainable artificial intelligence (XAI) techniques is proposed. The architecture is implemented on an example of a system for predicting the following purchases for time series using Long short-term memory (LSTM) neural networks and Shapley additive explanations (SHAP) values. The developed system was evaluated with three different LSTM neural networks for predicting the next purchase day, with the most complex network producing the best results across all metrics. Explanations generated by the XAI module are provided with the prediction results to the user to allow him to understand the system’s decisions. Another benefit of the XAI module is the possibility to experiment with different prediction models and compare input feature effects.

3 July 2025 in Water
Verified
Journal Article
Open access
PDF file
AĐAleksandar Đorđević
Aleksandar Đorđević
MCMilica Ciric
Milica Ciric
VMVuk Milošević
Vuk Milošević
DRDragan Radivojević
Dragan Radivojević
EZEdwin Zammit
Edwin Zammit
Milan GocićMilan Gocić
Milan Gocić
This paper examines the relationship between investment in water education and economic performance, focusing on the context of widening countries (EU Member States and Associated Countries with lower research and innovation performance). Through time-series data and panel regression analysis, the study investigates whether increased spending on education correlates with Gross Domestic Product (GDP) growth. While the initial static model indicates a positive but statistically insignificant association, a dynamic model with lagged GDP significantly improves explanatory power, suggesting that educational investments may influence growth with a temporal delay. Complementing the macroeconomic data, the paper analyses how targeted investments in educational innovation, especially in digital technologies such as virtual reality (VR) applications, enhance teaching quality and student engagement. Examples from partner universities involved in the WATERLINE project (Horizon Europe, 101071306) show how custom-built VR modules, aligned with existing hydraulic labs, contribute to advanced water-related skills. The paper also presents a cost-benefit analysis of VR applications in water education, highlighting their economic efficiency compared to traditional laboratory equipment. Additionally, it explores how micro-level innovations in education can generate macroeconomic benefits through widespread adoption and systemic impact. Ultimately, the research highlights the long-term value of education and innovation in strengthening both economic and human capital across diverse regions.

13 October 2025
Verified
Conference Paper
Closed access
MTMilica Tasić
Milica Tasić
Ivan Toplica CiricIvan Toplica Ciric
Ivan Toplica Ciric
MCMilica Ciric
Milica Ciric
MMMiljana Milić
Miljana Milić
BPBratislav Predic
Bratislav Predic
Due to the increasing prevalence of irregular sampling across various scientific disciplines, the analysis and forecasting of irregular time series has gained growing importance in contemporary research. Unlike regular time series, irregularly sampled data introduces specific challenges, including temporal misalignment, missing values, variable-length observations, and data sparsity. Recent literature presents a wide range of methodologies developed to address these challenges, with particular emphasis on the use of Explainable Artificial Intelligence (XAI). The aim of this paper is to identify and analyze XAI models that explicitly address irregularities in time series, including those capable of combining interpretability with the capacity to learn from sparse, temporally inconsistent, and nonlinear data. Furthermore, we discuss the importance of optimizing these models for deployment on edge devices in line with Industry 5.0 principles, emphasizing human-centric and transparent decision-making processes.


1 January 2026
Verified
Conference Paper
Open access
PDF file
AĐAleksandar Đorđević
Aleksandar Đorđević
Milan GocićMilan Gocić
Milan Gocić
VMVuk Milošević
Vuk Milošević
MCMilica Ciric
Milica Ciric
Financing green infrastructure requires arrangements capable of addressing high initial capital needs and long-term performance requirements. This paper examines the application of Public-Private Partnerships (PPPs) to renewable energy, energy-efficient buildings, and related forms of green infrastructure. The study combines a structured qualitative review of scientific and institutional sources with selected international and Serbian project cases. The analysis identifies risk allocation, life-cycle management, regulatory predictability, institutional capacity, and contractual design as important factors affecting PPP performance. International cases include energy-efficient public lighting, solar-energy development, and waste-to-energy infrastructure, while Serbian examples cover public-lighting and biomass-based heating projects in Niš, solar generation in Vranje, and the Vinča waste-management PPP in Belgrade. These applications are interpreted through an integrated conceptual framework linking infrastructure investment needs and project risks with PPP mechanisms and economic, environmental, and social outcomes. For Serbia, the findings also indicate potential for further application in public-building energy renovation, renewable-energy systems, low-carbon district heating, and urban green and blue infrastructure.