Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.4
3.1
Journals
Systems
Special Issues
Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education,...
share announcement

Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition)

A special issue of Systems (ISSN 2079-8954). This special issue belongs to the section "Systems Practice in Social Science".

Deadline for manuscript submissions: 31 December 2026 | Viewed by 4602

Special Issue Editor

Dr. Mingche Lee

E-Mail Website
Guest Editor
Applied Artificial Intelligence Department, Ming Chuan University, Taoyuan, Taiwan
Interests: deep learning; machine learning; IoT; AIoT; generative AI/LLM; FinTech
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Data-driven modeling and predictive analysis have become indispensable tools in understanding and shaping various aspects of our modern society. In the realms of business, social interactions, economics, and engineering, the integration of data-driven approaches has revolutionized decision-making processes and empowered organizations to anticipate trends, mitigate risks, and seize opportunities with greater precision and efficiency. This Special Issue aims to explore the multifaceted applications of data-driven modeling and predictive analysis within the contexts of business, social dynamics, economic trends, engineering, and education applications.

Key to this exploration are established data-driven approaches—including machine learning, deep learning, predictive analytics, and econometric modeling. Building on these foundations, recent progress in Advanced AI (e.g., LLMs and generative models) and interactive and immersive technologies (e.g., AR/VR/XR) provides complementary capabilities for knowledge extraction, interactive analytics, and human-in-the-loop decision support. Collectively, these methods enable large-scale data processing, the extraction of actionable insights, and improved forecasting performance across diverse applications.

This Special Issue invites contributions that delve into the application of data-driven modeling and predictive analysis in diverse contexts, including, but not limited to, the following:

* LLM-augmented and generative forecasting;
* Social network analysis and prediction;
* Economic forecasting and trend analysis;
* Engineering optimization and predictive maintenance;
* Financial market analysis and prediction;
* Supply chain optimization and demand forecasting;
* Customer behavior analysis and prediction;
* Infrastructure optimization;
* Immersive analytics with AR/VR/XR technologies;
* Long-term care engineering analysis and prediction;
* Healthcare engineering analysis and prediction;
* Environmental monitoring and prediction;
* Data-driven modeling in social and education (learning analytics, AI teaching assistants, academic integrity detection);
* Environmental protection and sustainable engineering.

By examining these diverse applications, we aim to showcase the versatility and effectiveness of data-driven approaches in addressing real-world challenges and driving innovation across various domains. We invite researchers and practitioners to contribute original research articles, reviews, case studies, and perspectives that highlight the advancements and opportunities in data-driven modeling and predictive analysis.

Dr. Mingche Lee
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Systems is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • optimization techniques
  • supply chain management
  • infrastructure planning
  • environmental impact analysis
  • decision support systems
  • data-driven innovation
  • real-time analytics
  • interdisciplinary applications
  • sustainable engineering
  • information-based systems
  • generative AI
  • large language models (LLMs)
  • retrieval-augmented generation (RAG)
  • AR/VR/XR
  • immersive analytics
  • learning analytics
  • digital twin
  • interactive technologies
  • human-computer interaction (HCI)
  • spatial computing
  • conversational agents

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issue

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 692 KB  
Article
Students’ Perceptions of the Use of Artificial Intelligence Tools in Educational Activities
by Octavian Dospinescu, Sabin Corneliu Buraga and Nicoleta Dospinescu
Systems 2026, 14(6), 633; https://doi.org/10.3390/systems14060633 - 2 Jun 2026
Viewed by 74
Abstract
The emergence of artificial intelligence (AI) tools, particularly generative models, in the last five years has fundamentally transformed the framework and methodologies of learning in higher education. Students are integrating AI for producing new ideas, assisted and personalized search, academic writing, advanced data [...] Read more.
The emergence of artificial intelligence (AI) tools, particularly generative models, in the last five years has fundamentally transformed the framework and methodologies of learning in higher education. Students are integrating AI for producing new ideas, assisted and personalized search, academic writing, advanced data analysis, and personalized learning. For this reason, an update of the theoretical and conceptual framework regarding the adoption of technologies in the educational environment is required. Based on traditional Technology Acceptance Model/Unified Theory of Acceptance and Use of Technology (TAM/UTAUT) models, we propose a new Partial Least Squares Structural Equation Modeling (PLS-SEM) model developed for the context of AI in higher education. The novelty of the model lies in the integration of the mediating relationship through trust (trust in AI outputs, TAIO) between perceived academic integrity risk (PAIR) and behavioral intention to use (BI), while anchoring perceived learning utility (PUL) and perceived effort expectancy (PEE) in AI literacy-specific self-efficacy (AILSE). The model is tested using a sample of 339 higher education students from economics and computer science specializations and validated using the R environment and the SEMinR package as specific software tools. Our proposed research hypotheses consider six reflective latent constructs and a mediating relationship, which we analyze using validated PLS-SEM techniques. All items included in the model constructs are formulated for use in university educational contexts and are adapted to specific AI tools for learning in the university environment. Full article
(This article belongs to the Special Issue Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition))
►▼ Show Figures

Figure 1

38 pages, 5804 KB  
Article
An Explainable Framework for ESG Portfolio Rebalancing with Transformer Models and Carbon Credit Signals
by Ming Che Lee
Systems 2026, 14(5), 563; https://doi.org/10.3390/systems14050563 - 15 May 2026
Viewed by 155
Abstract
This study proposes an explainable framework for ESG portfolio rebalancing by integrating carbon credit signals, technical indicators, and Transformer-inspired forecasting into a unified decision process. The investable universe consists of six ESG-themed ETFs, namely ESGU, SUSA, ICLN, TAN, KRBN, and KGRN. Carbon-related sustainability [...] Read more.
This study proposes an explainable framework for ESG portfolio rebalancing by integrating carbon credit signals, technical indicators, and Transformer-inspired forecasting into a unified decision process. The investable universe consists of six ESG-themed ETFs, namely ESGU, SUSA, ICLN, TAN, KRBN, and KGRN. Carbon-related sustainability information is represented by four S&P carbon indices, including GCC, CCA, EUA, and UCITS. Within the proposed framework, Transformer, Informer, and Temporal Fusion Transformer are used to predict next-day returns, and the forecast outputs are translated into portfolio decisions through threshold filtering, Softmax-based allocation, and inertia smoothing under fixed transaction costs. The empirical results show that the proposed framework remains competitive against Equal Weight, Risk Parity, and Momentum benchmarks, although its advantage is conditional rather than uniformly dominant across all metrics. Informer delivers the strongest Sharpe ratio among the model-based strategies, while Transformer exhibits a more stable risk profile. The ablation results indicate that the smoothing mechanism has the clearest effect on turnover and allocation stability, whereas the incremental value of carbon-related inputs is most visible in Informer. The uncertainty assessment further shows that many benchmark differences are not consistently significant under repeated resampling, but the performance weakening caused by removing carbon inputs in Informer remains identifiable. The subperiod analysis shows that benchmark rules are more competitive in 2024H1, whereas model-based strategies gain relative strength in 2024H2. The explainability analysis indicates that carbon-feature contributions are concentrated more strongly in Intermediate and Carbon-Sensitive asset groups and remain weaker in Broad ESG assets; feature-level and SHAP beeswarm evidence further shows that the three architectures rely on GCC, CCA, EUA, and UCITS in different ways. These findings suggest that carbon-related sustainability signals can provide economically meaningful allocation information in selected settings when they are combined with suitable model architecture and disciplined rebalancing control, thereby supporting a competitive and explainable ESG portfolio rebalancing framework. Full article
(This article belongs to the Special Issue Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition))
►▼ Show Figures

Figure 1

20 pages, 1652 KB  
Article
A New Interval-Valued Carbon Price Forecasting Paradigm: Mixed-Frequency Data-Driven Stacking Ensemble Forecasting System
by Yan Hao, Jingwen Zhang, Xin Wang, Jie Liu and Wendong Yang
Systems 2026, 14(3), 255; https://doi.org/10.3390/systems14030255 - 28 Feb 2026
Viewed by 533
Abstract
Accurate carbon price predictions are vital for supporting the effective functioning of the carbon market. Most existing studies rely on point-valued modeling, thus failing to fully explore interval-valued data and mixed-frequency information. To address this limitation, this paper proposes a new interval-valued carbon [...] Read more.
Accurate carbon price predictions are vital for supporting the effective functioning of the carbon market. Most existing studies rely on point-valued modeling, thus failing to fully explore interval-valued data and mixed-frequency information. To address this limitation, this paper proposes a new interval-valued carbon price forecasting paradigm and presents a mixed-frequency data-driven stacking ensemble forecasting system. The data preprocessing module in this system was designed to remove noise through signal decomposition and reconstruction. Additionally, the mixed-frequency modeling module integrates a mixed-frequency model, statistical model, and artificial intelligence model, which can fully utilize the significant potential of mixed-frequency information and overcome the limitations that result from selecting only one type of basic model. Moreover, a stacking ensemble learning module is proposed to fully exploit the advantages of the mixed-frequency modeling module, thereby providing more accurate forecasting results. Comparative experiments were performed and discussed based on the real carbon market, proving that the developed mixed-frequency data-driven stacking ensemble forecasting system outperforms other advanced methods and could provide an effective technique for improving carbon market management. Full article
(This article belongs to the Special Issue Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition))
►▼ Show Figures

Figure 1

28 pages, 2273 KB  
Article
Enhancing Reinforcement Learning-Based Crypto Asset Trading: Focusing on the Korean Venue Share Indicator
by Deok Han and YoungJun Kim
Systems 2026, 14(1), 111; https://doi.org/10.3390/systems14010111 - 21 Jan 2026
Viewed by 2082
Abstract
Crypto asset markets are often described as globally integrated. However, empirical evidence suggests that they remain segmented across exchanges and jurisdictions. One notable example is the Korean premium (i.e., Kimchi premium), which refers to persistent price gaps between Korean exchanges and offshore venues. [...] Read more.
Crypto asset markets are often described as globally integrated. However, empirical evidence suggests that they remain segmented across exchanges and jurisdictions. One notable example is the Korean premium (i.e., Kimchi premium), which refers to persistent price gaps between Korean exchanges and offshore venues. The Korean market accounts for a substantial share of global crypto trading activity. Therefore, this segmentation can affect price discovery and create opportunities for systematic trading. Motivated by the Korean premium, this study introduces the Korean Venue Share Indicator (KVSI). Based on the price discovery literature, KVSI is an interpretable venue-level indicator that uses the relative trading volume share between Korean and global exchanges. This study integrates KVSI into the state space of multiple reinforcement learning algorithms to evaluate whether venue-level information improves trading decisions. The results show that the proposed model with KVSI achieves statistically significant improvements in cumulative return (CR), Sharpe ratio (SR), and maximum drawdown (MDD) compared to the baseline model without KVSI. It also achieves higher CR and mixed effects on risk metrics (SR, MDD) relative to benchmark strategies. Additional analyses indicate that the performance gains from KVSI are market-regime-dependent. Overall, the findings have practical implications for developing cross-market systematic trading strategies by leveraging a venue-level indicator as a proxy for market segmentation. Full article
(This article belongs to the Special Issue Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition))
►▼ Show Figures

Figure 1

28 pages, 1486 KB  
Article
Data-Driven Efficiency Analysis of EU Higher Education Systems Using Stochastic Frontier Models
by Ioana-Alexandra Râlea, Carmen Pintilescu, Ștefănescu Iulia-Oana and Kamer-Ainur Aivaz
Systems 2026, 14(1), 49; https://doi.org/10.3390/systems14010049 - 31 Dec 2025
Cited by 1 | Viewed by 852
Abstract
This study investigates the efficiency of higher education systems across the 27 Member States of the European Union during the period 2017–2022, addressing increasing policy interest in data-driven decision support and optimization techniques for performance evaluation in education systems. Efficiency is assessed using [...] Read more.
This study investigates the efficiency of higher education systems across the 27 Member States of the European Union during the period 2017–2022, addressing increasing policy interest in data-driven decision support and optimization techniques for performance evaluation in education systems. Efficiency is assessed using Stochastic Frontier Analysis, an optimization-based econometric approach, applied to multiple output dimensions relevant to learning analytics: alignment between graduates’ skills and labour market requirements, scientific productivity measured by published articles, and the number of higher education graduates. The model incorporates key input variables, including the student–teacher ratio, public expenditure per student, research and development expenditure, and the number of academic staff, while controlling for real gross domestic product per capita. To support integrated efficiency measurement and information-based decision-making, multidimensional outcomes are aggregated into composite efficiency indices using entropy-based weighting. The results reveal substantial cross-country heterogeneity in efficiency across EU higher education systems, identifying a cluster of high-performing countries that consistently optimize scientific output and graduate production. Financial resources and academic staff availability emerge as significant drivers of efficiency, while skill matching to labour market demand remains a persistent structural challenge. By combining Stochastic Frontier Analysis with entropy-based aggregation, this study provides a robust data-driven decision support framework for efficiency assessment, offering valuable insights for education policy design, resource allocation, and learning-oriented system optimization. Full article
(This article belongs to the Special Issue Data-Driven Modeling and Predictive Analysis in Business, Social, Economic, Education, and Engineering Applications (2nd Edition))
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop