The research focuses on how Multi-Agent Systems (MAS) coupled with Machine Learning (ML) can help manage the challenges and risks associated with new-generation supply chains networks. The proposed MAS-ML framework improves flexibility, adaptability, and predictiveness in essential roles in supply chain management (SCM), including demand forecasting, inventory management, production planning, and SCM logistics. The framework is based on decentralised decision-making where each agent is responsible for a particular supply chain activity but employs real-time data foresight from the ML model to streamline the activities. This decentralisation enables resilience in supply chains, which can experience events such as demand variability and transportation disruptions. MAS-ML is presented in this paper as the solution capable of enhancing supply chain performance, reliability, and cost optimisation in situations characterised by risk and uncertainty, such as the current global pandemic. In addition, this paper presents potential research areas, such as the integration of more enhanced deep learning algorithms, the extension of proposing MAS-ML into other sectors, and the addressing of ethical and transparency concerns associated with AI-based decision-making systems. The proposed MAS-ML framework improves the adaptability and resiliency of supply chains, providing a flexible solution for modern supply chain problems.

In this study, we propose a predictive cybersecurity framework for the banking sector by integrating ensemble-based machine learning models. Our approach leverages heterogeneous datasets—including internal firewall and intrusion detection system logs, banking transaction records, user behavior data, and external threat intelligence—to capture a comprehensive view of the cyber threat landscape. Following rigorous data preprocessing, feature selection, and feature engineering, we evaluated multiple models, including Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Deep Neural Networks. Comparative analysis revealed that while advanced individual models demonstrated strong predictive capabilities, the Ensemble Model consistently outperformed all others, achieving an accuracy of 92% and a ROC-AUC of 94%. These results underscore the model’s superior ability to minimize false negatives, which is critical for safeguarding financial assets. Our findings advocate for the adoption of ensemble techniques in real-world banking cybersecurity applications, providing a robust, scalable solution that adapts to evolving threat patterns while significantly enhancing detection performance.

In recent years, Human AI Collaboration has become an exciting new approach to IT systems design that is designed to balance automation and human expertise. Specifically, this paper investigates a broad framework of smart scenario co-creation with IT systems in general, where human and AI work together in dynamically sharing IT tasks, AI provides decision tools for augmentation, and mutual performance is optimized by dynamically adjusting learning parameters. The research employs a mixed method, and the case studies together with the surveys and the quantitative data analysis are used to assess the existing collaboration models. We find that hybrid teams, consisting of both AI agents and human experts, increase productivity by up to 40% when executing iterative design processes. In addition, the study provides important insights regarding the critical success factors such as adaptive system interfaces, trust building mechanisms and the skill augmentation strategies. This information presents a path for overcoming ubiquitous challenge in utilizing collaborative frameworks, such as technological misalignment and user resistance. The proposed framework is intended to enable replication of such integration in the real time IT environment offering flexibility, scalability and long-term efficiency. Second, this research adds to the expanding repository of knowledge in terms of human centered AI development and offers IT leaders practical approaches to take advantage of human AI synergy for innovation and competitiveness.

The aim of this study is to advance multi-label delivery delay predictions in supply chains using machine learning and deep learning models. The work used Decision Trees, Random Forests, CNN, and FNN on a real-life logistics dataset consisting of customers and products features. EDA and feature selection were examined and performed as a part of the data preprocessing process at the pre-processing step of the models. According to current model results, Random Forest model reached maximum accuracy of 66.5% along with Decision Trees and FNN. CNN, although, worked well in some instances was not up to par in some areas because it overfitted. The results also reveal how Random Forest is a particularly useful algorithm for predicting delivery delays accurately. The conclusion suggests enhancing the deep learning models performance and combining approaches. Further work should also incorporate other variables in order to improve the predictive capability in real-life requirements of supply chain environments including conditions and stocks.

This study investigates the influence of mold thickness on the cooling rate and hardness of gray cast iron in two distinct mold types: metal and sand molds. The experiment is conducted by casting gray cast iron in molds of varying thickness and measuring the cooling rate and hardness at different intervals during solidification. The results indicate that both mold type and thickness significantly affect the cooling rate and the hardness properties of the cast iron. Metal molds lead to faster cooling and higher hardness, while sand molds show slower cooling rates and lower hardness. This study provides insight into how mold design and thickness can optimize casting quality and material properties for industrial applications.

The article analyzes the development of an automated system designed to inform about discounts offered by competitors on the clothing e-commerce platform. The main goal was to replace manual data collection and integration processes with an automated approach that improves the accuracy of company pricing steering strategy and reduces operational overhead. The system model is based on Lagrange equations, which ensures the integration of price information into strategic management.

The implementation methodology includes web scraping through Selenium, scrappy tools, and data processing using machine learning methods. The approach to analyzing text materials allows you to effectively extract meaningful information from advertising content. The architectural solution is based on a microservice model, which increases the adaptability of the system and simplifies scaling. Existing scientific research, studies, and developments, as well as the author's practical experience working on a commercial e-commerce fashion platform, were used as sources, allowing for a comprehensive exploration of the topic.

The results demonstrate cost reduction and improved accuracy of processes related to pricing. The developed system finds applications in e-commerce, marketing, data processing, and software development, where automated solutions for business process management are in demand.

The study presents a method for collecting and analyzing data on competitors' price offers. The developed system uses big data processing algorithms to monitor changes in pricing policy. This allows you to quickly adapt pricing strategies, as well as make adjustments to marketing decisions.

The formulated conclusions confirm the achievement of the stated goals. The introduction of an automated approach has made it possible to optimize tasks related to monitoring and analyzing competitive offers as well as ensuring pricing steering accuracy, i.e. meeting certain business targets on total sales discount rates.

The challenge of enhancing IT service delivery lies mainly in incorporating real-time user feedback to adapt solutions. Research investigates how AI sentiment analysis helps IT service management by supplying data-driven information for enhancement. The system uses modern natural language processing (NLP) models especially Bidirectional Encoder Representations from Transformers (BERT) to extract and categorize user sentiment from feedback obtained from multiple sources that include service tickets and customer surveys. Research findings demonstrate that negative customer sentiments create service delays which resulted in predictive systems that handle cases more efficiently and reorder service tasks according to importance. When teams employed sentiment-based methods they cut ticket resolution duration down by 35% and user satisfaction strengthened by 22%. The study provides scholars with a flexible system that combines AI-based sentiment evaluation with IT service management processes. The system shows its ability to adapt through automated responses which interact with changing expectational needs and emerging feedback patterns. Any implementation of AI requires focused attention on ethical elements such as how users' privacy will be maintained and the processes by which consent is secured. Sentiment analysis presents a valuable tool which helps providers maintain user need anticipation abilities alongside their capability to prevent bottlenecks and regulate performance statistics. Researchers should study how the integration of sentiment data with behavioral information might create service personalization models of higher quality. The paper provides applicable guidance to IT managers and policymakers which features sentiment analysis as an essential element that drives adaptable user-oriented service enhancement approaches.

New developments in Artificial Intelligence (AI) in IT services have drastically altered how companies use customer insights to supply personalized and scalable responses to a wide variety of client necessities. The focus of this study consists in the use of AI tools and algorithms in customer data analysis, but also in the sense that they are useful for providing targeted and efficient IT service solutions. The findings are robust because a mixed-methods approach was employed, using qualitative analysis of case studies and quantitative evaluations of service outcomes. The results show that adding AI features into workflows of IT services can significantly improve satisfaction metrics for customer, operating efficiency, and the scalability of the service overall. Additionally, the paper organizes frameworks and different strategies for utilizing AI devices and investigating issues, for example, data secrecy, calculation predisposition, and extendibility. This research also helps bridge a few of the existing gaps in the existing body of knowledge about potential AI applications in customer–centric IT service and provides actionable insights for practitioners and policymakers. The main takeaways indicate how much organizations need to start seeing AI as a business growth strategy and not as a technological advancement. Related to this, future research needed to understand the ethical considerations of artificial intelligence in customer insights, and the overall implications of artificial intelligence, in the context of media distributors and different cultural and regulatory environments.