Satyadhar Joshi

Mr. Satyadhar Joshi

Risk Analytics, Bank of America, Charlotte, Michigan, USA
orcid
Available for Review / Volunteering to contribute in Academi...

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
28 February 2025 in World Journal of Advanced Engineering Technology and Sciences
Verified
Journal Article
Closed access
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
Artificial Intelligence (AI) agents are revolutionizing industries by enabling autonomous decision-making, task execution, and multi-agent collaboration. This paper provides a comprehensive review of AI agent frameworks, focusing on their architectures, applications, and challenges in financial services. We conduct a comparative analysis of leading frameworks, including LangGraph, CrewAI, and AutoGen, evaluating their strengths, limitations, and suitability for complex financial tasks such as trading, risk assessment, and investment analysis. The integration of AI agents in financial markets presents both opportunities and challenges, particularly in terms of regulatory compliance, ethical considerations, and model robustness. We examine agentic AI design patterns, multi-agent systems, and the deployment of AI agents advancing the proposal to use them for fraud detection and risk management. By synthesizing insights from academic research and industry practices, this review identifies key trends and future directions in AI agent development. This work contributes to the growing discourse on AI-driven automation by outlining technical considerations and open challenges in deploying AI agents at scale. We highlight the need for enhanced transparency, interpretability, and security in AI-driven Agentic systems. Our findings provide valuable insights for researchers and practitioners seeking to harness AI agents for more efficient and intelligent decision-making.

18 January 2025 in International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Verified
Journal Article
Open access
PDF file
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
In this paper, we propose and demonstrate a prototype for leveraging Generative AI (GenAI) in financial risk analysis, specifically focusing on fine-tuning GPT models with proprietary data. Financial risk modeling, development, validation, and approval require not only advanced AI techniques but also careful implementation, given the vast and complex datasets involved in such tasks. The research underscores the critical importance of human oversight in mitigating potential failures that can arise from fully automated mathematical models. The study explores the application of Large Language Models (LLMs) in various financial risk domains, such as credit risk assessment, market risk forecasting, and anomaly detection. While synthetic data generation is excluded from this work, the research highlights the use of zero-shot classification leveraging Hugging Face models and OpenAI tools. ChatGPT achieved over 70% accuracy in generating relevant questions and demonstrated 60% correctness in classification tasks. Additionally, we present a prototype pipeline that integrates GenAI capabilities into financial workflows, which is implementable on small-scale computing systems. This includes backend testing via Flask and rapid prototyping using cURL commands, offering a practical approach to testing and deploying models. By fine-tuning GenAI with domain-specific data and optimizing decision-making processes, this research highlights the transformative potential of integrating generative AI into financial risk management. The study provides insights into enhancing model efficiency, regulatory compliance, and scalability. Moreover, it addresses critical challenges such as handling large datasets and ensuring ethical AI use in decision-making systems. This work contributes to advancing the adoption of GenAI in financial analytics, paving the way for innovative, robust, and efficient methodologies to support the evolving demands of the financial sector.

30 January 2025 in World Journal of Advanced Research and Reviews
Verified
Journal Article
Closed access
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
This paper presents a comprehensive investigation into the role of prompt engineering in optimizing the effectiveness of large language models (LLMs) like ChatGPT-4 and Google Gemini for financial market integrity and risk management. As AI tools are increasingly integrated into financial services, including credit risk analysis, market risk evaluation, and financial modeling, prompt engineering has become crucial for improving the relevance, accuracy, and contextual alignment of AI-generated outputs. This study evaluates the impact of various prompt configurations in enhancing financial decision-making. Through a series of experiments, the paper compares the performance of ChatGPT-4 and Google Gemini (versions 1.5 and 2.0) in generating actionable insights for credit and market risk analysis. The results reveal that ChatGPT-4 outperforms Google Gemini by over 30% in generating accurate financial insights. Additionally, ChatGPT-4 Version 4 is found to be 20% more effective than Version 3 in risk analysis tasks, particularly in aligning with regulatory frameworks and financial data. These improvements highlight the significant role of prompt engineering in enhancing the precision of financial models. Furthermore, the study explores the reduction of error rates through optimized prompt strategies. In particular, prompt engineering reduces error rates by approximately 20% when assessing complex financial queries.

5 February 2025 in International Journal of Research and Review
Verified
Journal Article
Closed access
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
This paper presents a systematic review of generative AI applications in workforce development and education. We categorize the literature into key themes and synthesize findings to highlight trends, challenges, and future directions. Expected outcomes include enhanced training efficiency, broader accessibility to high-quality learning resources, and reduced costs compared to traditional methods. The AI-driven approach ensures adaptability across industries, providing a scalable solution for continuous workforce upskilling. However, challenges such as data privacy, algorithmic bias, and user adoption must be addressed through stringent security measures, bias mitigation strategies, and user-friendly interfaces. By harnessing generative AI, this initiative aims to revolutionize professional training, equipping individuals with the tools to adapt to an evolving job market. Additionally, this paper proposes AI-driven training programs specifically tailored for older workers, addressing the AI skills gap and ensuring workforce inclusivity. The successful implementation of AI-driven training agents will not only improve productivity but also foster a culture of lifelong learning, empowering workers to thrive in an AI-enhanced economy. Furthermore, this paper utilizes various graphical representations, including decision trees, heatmaps, and trend analysis charts, to illustrate the projected impact of generative AI on workforce development. These visual tools provide a comprehensive and data-driven perspective on emerging trends, enabling readers to grasp complex interconnections and future scenarios effectively. If trends continue along their projected paths, AI-driven workforce transformation could reshape industries on an unprecedented scale, requiring proactive adaptation strategies from policymakers, businesses, and individuals alike. This review is based on latest research published in last one year. Keywords: GEN AI, Agents, US Workforce Development, US Competitiveness

1 December 2024 in International Journal of Innovative Research in Engineering and Management
Verified
Journal Article
Open access
PDF file
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
With Gen AI models becoming more evolved, their application in enhancing the robustness of the US Financial System is more viable. Financial risk modeling can take advantage of these development and aid regulatory framework by integrating these novel technologies to make their models more robust. In this work, we have used the latest Gen AI model by Open AI also known as Chat-GPT 4o and 40 mini and Google Gemini Version 2.0 and 1.5 to generate relevant questions from govt websites and measure the accuracy and relevance in checking the the pre trained logistic regression models. We have rated the accuracy of the questions by taking a survey of three Risk Analysts (volunteers) and found that Gen AI is 70-80% accurate in terms of the question for the models it generated. The new and the old model for open ai vs Gemini were compared. We have also documented how different models are sensitive to different prompts as they want to save computational cost and keep the output relevant. These questions generated can be used and integrated in the backend and auto curate the models under analyst supervision. We proposed a full stack framework as an end to end solution to address issues related to privacy and ethical considerations limiting exposure of property data and models. We have used all-MiniLM-L6-v2 as the bridging APIs for creating variants of the queries.

1 June 2025 in International Journal of Innovative Research in Engineering and Management
Verified
Journal Article
Open access
Satyadhar JoshiSatyadhar Joshi
Satyadhar Joshi
Artificial Intelligence (AI) landscape is fast developing such that there are dynamic and autonomous representatives of AI which are referred to as AI agents. These agents, fueled by the evolution of generative AI and large language models (LLMs), can make their own decisions, perform tasks and make adjustments to rapidly changing environments. An even more advanced step is the instrumentation of various specialized AI agents into working multi-agent systems (MAS). The paper will discuss the disruptive effect of the introduction of AI agents and MAS on the automation and service of enterprises and different industries. We look into their possibilities, various uses, and the natural strengths and weaknesses, such as the essentiality of effective governance infrastructure and complicated conditions in human-AI partnership. Although promising new levels of efficiency and capability to solve problems previously inaccessible, ethical implications associated with the use of these agentic systems have to be carefully explored as well as the approaches to integration that should be able to guarantee their long-term value and be serving to empower humans. This paper is a survey paper regarding Agentic AI and multi-agent systems within the enterprise context. Examining 65 of thes contemporary sources (2024-2025), we record the paradigm shift of passive generative AI to autonomous agentic systems. The paper analyses the architectural structures, models of collaboration, industrial use and governance issues. The most significant ones are (1) multi-agent systems have a 40-60% efficiency gain of the processes, (2) special agent relation coordination protocols are becoming important infrastructure, and (3) it is found that human-agent collaboration needs new stewardship and motivational models. All these are ended in the paper with new directions of agent-to-agent communications and the specific agent settings.