Journal of Big Data Technology and Business Analytics

TradeWarNet: A Causal Attention-based Graph Framework for Analysing Trade War Shocks in Financial Markets

Sharad Pandurang Latkar, Charvak Nangare — Thu, 29 Jan 2026 00:00:00 +0000

In the prevailing global economic environment, renewed trade tensions, selective tariff measures, and strategic trade interventions have significantly influenced financial market dynamics. These trade war-related shocks generate complex, time-varying, and cross-market effects that are difficult to capture using traditional econometric and correlation-based machine learning approaches. In this paper, TradeWarNet, a causal and attention-based graph learning framework designed to quantify and interpret the impact of trade war shocks on global financial markets is proposed. The proposed framework integrates causal event modelling to isolate trade-induced effects from broader macroeconomic influences and employs a temporal graph attention network to capture dynamic shock transmission across equity, foreign exchange, and commodity markets. Empirical analysis using multi-asset data from both developed and emerging economies demonstrates that TradeWarNet achieves improved volatility forecasting performance, enhanced structural break detection, and greater interpretability compared to benchmark models. The results further indicate that emerging markets exhibit higher sensitivity to trade war shocks under current market conditions, while select safe-haven assets display stabilizing characteristics. The proposed framework offers a policy-relevant and interpretable machine learning approach for analyzing trade-related financial risks.

Extended Reality (XR) as the Next Generation of Interactive and Reality-based Digital Experiences: Applications, Benefits, and Challenges

Vijayalakshmi P. S., Dharani V., Monica Jenifer J. — Wed, 18 Feb 2026 00:00:00 +0000

The extended reality (XR) is a new modality of creation of interactive, context-driven digital experiences. As a way to determine the effects of XR technologies in modifying human interaction both in the virtual and the physical world, it explores the main XR technologies, namely virtual reality (VR), augmented reality (AR), and mixed reality (MR). The study adopts a systematic approach that explores the current academic works, industry reports and empirical case studies in the field. It classifies the XR applications into fields including education, healthcare, manufacturing, entertainment and training. The different XR modalities are comparatively analyzed in an effort to determine the efficacy, the technologies necessary, and the practical challenges. related to implementation. Results showed that XR results in better interaction with participants and experiential learning, as well as informative decision-making due to realistic and interactive simulations. In addition, XR enhances the observational clarity, provides safer training environments and provides cost-efficient operating models. However, major barriers such as costing a lot of capital to install the equipment, technical constraints, privacy, ethical issues, and lack of standardization that is universally accepted are all challenges to the adoption of XR technologies.

Governance and Evaluation Framework for Agentic AI Systems in Enterprise Operations

Sandeep Mahajan — Tue, 24 Feb 2026 00:00:00 +0000

The increasing deployment of agentic artificial intelligence (AI) systems, autonomous agents capable of perceiving, reasoning, and acting independently, within enterprise operations, introduces governance and evaluation challenges that existing frameworks do not address. Prevailing AI governance models primarily target static or semi-autonomous systems, overlooking the dynamic, self-directed behaviors of agentic AI that complicate accountability, ethical compliance, and organizational integration. This study develops a preliminary expert-informed governance and evaluation framework specifically for agentic AI in enterprise contexts. Using a multi-method qualitative design, the research integrates a systematic literature review with semi-structured interviews of domain experts in AI governance, ethics, and enterprise deployment. The resulting framework synthesizes technical, ethical, and organizational dimensions, incorporating multi-faceted evaluation metrics, trajectory-based assessments, and adaptable human oversight aligned with operational risk. Expert input highlights the critical role of organizational readiness, role clarity, and collaborative leadership for effective implementation. This research advances a practical and actionable governance paradigm that supports responsible deployment and continuous evaluation of agentic AI systems, bridging theoretical understanding with enterprise practice and enabling organizations to leverage autonomous AI technologies sustainably and ethically.

AI-enabled Robotic Multi-machine Operation and Intelligent Production Management System

Mon, 02 Mar 2026 00:00:00 +0000

In modern manufacturing industries, efficient utilization of resources and reduction of machine idle time are critical for improving productivity. Traditional multi-machine operation systems, whether manual or pre-programmed robotic, often lack adaptability, intelligent decision-making, and real-time production optimization. This study presents an AI-enabled robotic multi-machine operation and intelligent production management system designed to enhance manufacturing efficiency and automation. The proposed system integrates industrial robots with multiple CNC machines and employs artificial intelligence techniques to enable dynamic task scheduling, intelligent machine allocation, and real-time decision-making based on machine status and production requirements. Specifically, a deep reinforcement learning (DRL) model is implemented to learn optimal scheduling and resource allocation strategies from historical and real-time machine data. Machine data, such as cycle time, availability, and operational status, is collected and analysed using AI algorithms to optimize robot movements and production flow. The system aims to minimize machine idle time, improve overall equipment utilization, and reduce human intervention. Experimental results and performance analysis demonstrate that the AI-driven approach significantly improves production efficiency compared to conventional robotic systems. This research highlights the potential of combining artificial intelligence, robotics, and computer engineering to achieve smart manufacturing solutions aligned with Industry 4.0 principles.

Big Data in the Modern Era: Technological Advances, Management Practices, and Research Challenges

Shreya V. Varute, Vijaya E. Patil, Shrutika S. Patil, Swapnali A. Salunkhe — Sat, 28 Mar 2026 00:00:00 +0000

In the modern digital era, big data has evolved from a technical buzzword into a fundamental shift in how people understand the world. Big data is more than just large data; it is about gaining valuable insights from complex and voluminous data sources. Big data is more than just “large files”, as it encompasses the vast amounts of complex data created from social media interactions to medical sensors. This study discusses the movement of big data and the significance of the large amount of information in identifying subtle population patterns that small-scale data often misses. However, from a logical perspective, bigger is not always better. A researcher must navigate significant computational and statistical hurdles. These include storage bottlenecks and the “noise accumulation” trap, where high dimensionality leads to spurious correlations—mathematical patterns that look real but are actually accidental. To bridge the gap between theory and practical application, this study examines the shift toward “Analytics 3.0.” This paradigm requires traditional IT infrastructures to coexist with flexible, open-source technologies like Hadoop. By analysing current management styles and privacy concerns, this review emphasises that the future of big data depends on a new statistical paradigm. To achieve a competitive advantage, organisations must transcend the traditional approach of gathering information.

A Smart Management System for Optimizing Campus Canteen Operations

Thu, 02 Apr 2026 00:00:00 +0000

Traditional campus food services encounter high levels of inefficiency due to lengthy wait times, human error in order taking, and a lack of access to important business data in real-time. This paper introduces a holistic smart food service management system that will offer a complete digital solution to these problems. This web-based system will provide users with the ability to reserve seats electronically, view menus online, order their meals online, manage complaints, and monitor all activities within the dining facility. The solution is designed using MERN (MongoDB, Express.js, React, Node.js) as the underlying technology stack. The system has been built with a focus on developing a secure and scalable website based on a solid database schema and effective user access controls to provide organisations with real-time reporting on business operations. Analysis has shown that the system has decreased service time by 67% while increasing the accuracy of orders by 95%, thereby improving operational transparency and efficiency. This system represents a possible approach to modernising the food service operations at higher education institutions and providing actionable business intelligence to assist administrators in their decision-making regarding their respective businesses.