In the face of increasing financial uncertainty and market complexity, this study presents a novel risk-aware financial forecasting framework that integrates advanced machine learning techniques with intuitionistic fuzzy multi-criteria decision-making (MCDM). Tailored to the BIST 100 index and validated through a case study of a major defense company in T\"urkiye, the framework fuses structured financial data, unstructured text data, and macroeconomic indicators to enhance predictive accuracy and robustness. It incorporates a hybrid suite of models, including extreme gradient boosting (XGBoost), long short-term memory (LSTM) network, graph neural network (GNN), to deliver probabilistic forecasts with quantified uncertainty. The empirical results demonstrate high forecasting accuracy, with a net profit mean absolute percentage error (MAPE) of 3.03% and narrow 95% confidence intervals for key financial indicators. The risk-aware analysis indicates a favorable risk-return profile, with a Sharpe ratio of 1.25 and a higher Sortino ratio of 1.80, suggesting relatively low downside volatility and robust performance under market fluctuations. Sensitivity analysis shows that the key financial indicator predictions are highly sensitive to variations of inflation, interest rates, sentiment, and exchange rates. Additionally, using an intuitionistic fuzzy MCDM approach, combining entropy weighting, evaluation based on distance from the average solution (EDAS), and the measurement of alternatives and ranking according to compromise solution (MARCOS) methods, the tabular data learning network (TabNet) outperforms the other models and is identified as the most suitable candidate for deployment. Overall, the findings of this work highlight the importance of integrating advanced machine learning, risk quantification, and fuzzy MCDM methodologies in financial forecasting, particularly in emerging markets.

Online banking continues to grow in popularity due to its convenience, but banks face significant challenges in ensuring secure customer identity verification. Traditional authentication methods such as PINs, passwords, and one-time passwords have shown limitations, especially in the wake of the COVID-19 pandemic, which accelerated the demand for seamless and contactless solutions. Voice biometrics have emerged as a reliable alternative, offering enhanced fraud protection and a more user-friendly experience. In Malaysia, this technology enables customer verification without the need for PINs or security questions. This study proposes an advanced authentication approach that integrates keystroke dynamics and voice biometrics within a multi-factor authentication framework. By leveraging artificial intelligence and fuzzy logic, the system aims to deliver heightened security and a smoother user experience. The goal is to provide Malaysian online banking users with a safer and more secure digital environment.

: Traffic represents a complex field containing many challenges, especially for decision-makers responsible for traffic management. One of its most significant areas is the management of signalised intersections with regard to pedestrian behaviour. Measuring the start-up time of pedestrians and its influence on the rest of the traffic participants is necessary. This paper proposes a new interval fuzzy rough MCDM (Multi-Criteria Decision-Making) framework in order to conduct a complex analysis of different intersections in five selected cities in Bosnia and Herzegovina and Serbia with regard to pedestrian behaviour. The proposed model combines the IFRN SWARA (Interval Fuzzy Rough Number Stepwise Weight Assessment Ratio Analysis) and IFRN CRADIS (Compromise Ranking of Alternatives from Distance to Ideal Solution) methods, representing novelty from a scientific perspective. The main methodological contribution of this research consists in developing an extension of the CRADIS method based on IFRNs. The IFRN SWARA method is applied for calculating the weights of the employed criteria, while the selected cities are ranked by using the IFRN CRADIS method. The research involved many intersections with and without countdown displays and a sample of over 10,000 pedestrians, which is enough to draw solid conclusions. The verification tests carried out confirm the obtained results, proving that the proposed model is stable.

The requisition for maintainable constructions has been greatly raising over the last several years. To fulfil the maintainability necessities of a construction, decisions or changes must be done to a construction in the course of the preconstruction and design steps. This can be plausible utilizing building information modelling. To indicate the utilize of building information modelling in maintainable planning, an example nursing-house is received for modelling research. The energy efficiency of nursing-home is analysed utilizing Autodesk Revit and Green Building Studio simulation which contained different characteristics such as annual heating and cooling loads, annual energy usage. Through using the utilize of different building, insulation and roof materials in the nursing-home modelling, the nursing-home modelling is changed into a greener construction modelling. In addition, the effects of using green walls on the facade of the building on the energy performance were analysed. Utilizing simulation, the utilize of non-natural sources can be dramatically decreased through substituting for them with the utilize of sustainable natural sources by that means energy saving. Building information modelling has substantiated to be effective in providing maintainability with alternative material’s assessment and earlier decision-making. Furthermore, this study employed an integrated new MCDM model to evaluate the performance of four natural stones for utilize in a nursing home setting.

Efficient decision-making in fruit production involves evaluating multiple criteria, such as yield, fruit quality, and resistance, to rank available alternatives. Multi-Criteria Decision-Making (MCDM) methods provide a structured and objective framework for such tasks. This paper presents a web-based application named FRUITrank, designed to implement the MARCOS MCDM method for ranking and selection of plum varieties. The application uses a predefined set of criteria, whose weights were determined externally by using other MCDM methods. By leveraging a simple and intuitive interface, the application aims to overcome barriers to the practical adoption of MCDM methods among researchers and fruit producers, such as mathematical complexity and lack of accessible tools. The application was tested using a set of 11 criteria relevant to plum production, demonstrating its capability to deliver reliable and transparent rankings. This paper builds upon prior research in MCDM applications for agriculture, offering a practical solution for producers and researchers to enhance decision-making processes. Future improvements to the developed tool may include automated criteria weight calculation and broader applicability across various agricultural contexts.