Journal of Science Engineering Technology and Management Science

Financial analysis is fundamental to understanding the performance and stability of banks. Traditionally, it involves examining financial statements, ratios, and market trends to assess profitability, liquidity, and risk. However, the banking sector today operates in a highly datadriven environment where conventional methods may not fully capture complex, hidden patterns.This study begins with a comprehensive financial analysis of Axis Bank using traditional tools and techniques, followed by an extension into Machine Learning (ML) and Deep Learning (DL) methodologies. By leveraging historical financial data, stock prices, and macroeconomic indicators, the study builds predictive models using algorithms such as Random Forest, Support Vector Machines, and Long Short-Term Memory (LSTM) networks. These models aim to forecast future trends, detect anomalies, and identify significant factors influencing Axis Bank's performance.The integration of ML and DL enhances the depth and accuracy of the analysis, demonstrating the transformative potential of artificial intelligence in modern financial research and decision-making

Keywords :

Author : A.Srikanth, Dr.M.Pavani ,G.Uma Maheshwari

Title : STUDY OF FINANCIAL ANALYSIS OF AXIS BANK

Volume/Issue : 2025;02(05(1))

Page No : 1-5

Financial statement analysis remains a cornerstone for evaluating a company's performance, profitability, and sustainability. Tata Consultancy Services (TCS), as one of India’s largest IT firms, has consistently delivered strong results, yet traditional financial analysis methods often fail to uncover deeper, hidden trends or forecast future movements effectively.This study starts with a comprehensive financial statement analysis of TCS using conventional techniques such as ratio analysis, trend analysis, and vertical & horizontal analysis. It then extends to advanced analytics by applying Machine Learning (ML) models like Random Forest and Gradient Boosting to predict profitability and revenue growth, and Deep Learning (DL) models such as Long Short-Term Memory (LSTM) networks to forecast time-series financial data.Combining traditional and AI-driven approaches not only validates the historical financial health of TCS but also reveals new insights and predictive capabilities, highlighting the transformative role of ML and DL in modern financial analysis.

Keywords :

Author : Dr.M.Ramakanth Reddy,R.Srilekha,Jella Ashwitha

Title : FINANCIAL STATEMENT ANALYIS OF TCS

Volume/Issue : 2025;02(05(1))

Page No : 6-10

Investment banks generate revenue through a range of complex and dynamic fee structures, including advisory fees, underwriting spreads, success fees, and retainers. Traditionally, fee determination and analysis have relied on historical averages, industry benchmarks, and linear models, often missing deeper relationships hidden within vast deal datasets. This study begins with a comprehensive analysis of investment bank fee structures, examining how fees vary by deal type, size, sector, region, and economic context.By extending the research to include Machine Learning (ML) and Deep Learning (DL) techniques, we aim to reveal non-linear patterns and identify the key drivers of fee variability that traditional methods overlook. ML models such as Random Forest and XGBoost are applied to predict fee percentages based on deal characteristics, client type, and market conditions, providing clearer insight into pricing strategies. In parallel, LSTM networks are used to forecast time-series trends in aggregate fee income, capturing seasonality and market cycles in a way that linear forecasting cannot.Our integrated approach demonstrates that AI models not only enhance forecasting accuracy but also uncover complex interactions between variables like market volatility, deal complexity, and client segment. The findings offer actionable insights for banks to design competitive yet profitable fee strategies and better align resources with market demand. Overall, this study illustrates the power of combining traditional financial analysis with modern AI tools to transform decision-making and strategy in investment banking.

Keywords :

Author : Dr.P.Janaki Ramulu,K.Archana,K.Sravanthi

Title : INVESTMENT BANK FEE STRCTURES

Volume/Issue : 2025;02(05(1))

Page No : 11-15

Reliance Industries Limited (RIL) and its telecom arm, Reliance Jio, represent two pillars of one of India's largest and most diversified conglomerates. Traditional financial analysis methods—such as ratio analysis, trend analysis, and common-size statements—help assess profitability, growth, and financial health over time. However, these methods often fail to uncover deeper, nonlinear patterns or accurately forecast future financial trends in dynamic sectors like telecom and energy.This study combines a conventional financial statement analysis of RIL and Jio with advanced predictive analytics. We apply Machine Learning (ML) models, including Random Forest and XGBoost, to identify the key drivers of profitability and predict revenue and net profit based on historical financial data and macroeconomic factors. Additionally, Deep Learning (DL) models, specifically Long Short-Term Memory (LSTM) networks, are employed to forecast time-series trends in quarterly revenue and stock prices.Our results reveal how the performance of Jio’s high-growth digital business contrasts with RIL’s diversified portfolio, highlighting sector-specific volatility and stability. The integration of AI-driven models not only enhances forecasting accuracy but also uncovers hidden interactions between business segments, market sentiment, and external economic indicators. The study underscores the transformative potential of combining traditional financial analysis with ML and DL to gain deeper strategic insights and improve forecasting precision.

Keywords :

Author : Dr.K.Shiva Keshav Reddy,L.Yamuna,K.Padya sree

Title : FINANCIAL ANALYSIS OF RELIANCE AND JIO

Volume/Issue : 2025;02(05(1))

Page No : 16-21

Capital management is central to ensuring a company’s long-term solvency, growth, and ability to maximize shareholder value. It involves balancing equity and debt financing, maintaining optimal liquidity, and making strategic decisions regarding asset utilization and retained earnings. Traditionally, capital management analysis relies on financial ratios, trend analysis, and static models. However, such methods often fail to capture complex, dynamic interactions among internal financial policies, market conditions, and macroeconomic changes.This study begins with a comprehensive review of capital structure, working capital policy, and dividend decisions to assess their collective impact on firm performance. To enhance the analysis, Machine Learning (ML) techniques like Random Forest and XGBoost are used to predict capital adequacy and optimal debt-equity mix, while Deep Learning (DL) models like LSTM networks forecast future capital requirements based on historical financial data and market trends. By integrating these AI-driven approaches, the study reveals nonlinear dependencies and patterns overlooked by traditional models, offering richer, more actionable insights for managers and investors alike.

Keywords :

Author : Dr.A.Anil Kumar Reddy,K.Vanajakshi,K.Akhila

Title : STUDY OF CAPITAL MANAGEMENT

Volume/Issue : 2025;02(05(1))

Page No : 22-26

Risk management is at the heart of investment banking, where institutions face a spectrum of risks including market risk, credit risk, liquidity risk, and operational risk. Traditional risk management relies heavily on Value at Risk (VaR), stress testing, scenario analysis, and expert judgment to measure, monitor, and mitigate these exposures. However, these methods often assume linear relationships and static volatility, which may fail to capture real-world complexities and sudden market shocks.This study combines conventional risk management frameworks with advanced analytics. Using Machine Learning models like Random Forest and XGBoost, we aim to detect hidden, nonlinear risk factors and predict potential losses more accurately. Additionally, Deep Learning models such as LSTM networks are employed to forecast time-series risk metrics like daily VaR and liquidity ratios, effectively capturing volatility clustering and long-term dependencies in financial data.By integrating ML and DL into risk analysis, the study demonstrates significant improvements in predictive accuracy and early warning capabilities, offering investment banks a more dynamic and data-driven approach to risk management

Keywords :

Author : Dr.K.Shiva Keshav Reddy,L.Yamuna,K.Narendra

Title : RISK MANAGEMENT IN INVESTMENT BANKING

Volume/Issue : 2025;02(05(1))

Page No : 27-31

Financial ratio analysis is a cornerstone of corporate financial evaluation, widely used by managers, investors, and researchers to measure an organization’s operational efficiency, liquidity, profitability, and solvency. This study focuses on Mother Dairy, a key player in India's cooperative dairy industry, whose unique seasonal demand patterns and dependence on agricultural supply chains create distinct financial challenges.Traditional ratio analysis reveals important trends over time, but remains lagely descriptive and backward-looking. To address this limitation, this study integrates modern AI tools, applying Machine Learning (ML) models such as Random Forest and XGBoost to identify critical financial ratios that most significantly impact profitability. Further, Deep Learning (DL) models, specifically Long Short-Term Memory (LSTM) networks, are used to forecast key ratios like current ratio and profit margins, capturing seasonality and volatility that conventional models often miss.The results show that AI-enhanced analysis not only increases forecasting accuracy but also uncovers subtle patterns and drivers, transforming static financial ratio analysis into a dynamic, data-driven decision-support tool

Keywords :

Author : Prof.Shaik.Aseen Babu,A.Srikanth,K.Shiva Reddy

Title : FINANCIAL RATIO ANALYSIS OF MOTHER DAIRY

Volume/Issue : 2025;02(05(1))

Page No : 32-38

This study undertakes an advanced and comprehensive financial statement analysis of Bank of Baroda, one of India's leading public sector banks, by strategically integrating traditional financial ratio analysis with cutting-edge Machine Learning (ML) and Deep Learning (DL) methodologies. Acknowledging the inherent limitations of conventional static analysis in capturing the complex dynamics of the banking sector, the research will systematically collect and scrutinize Bank of Baroda's audited financial statements over a significant 5-10 year historical period (e.g., FY2015-FY2024). This extensive dataset will first be used to compute a nuanced array of bank-specific financial ratios spanning critical dimensions such as liquidity (e.g., Advances to Deposits Ratio), profitability (e.g., Net Interest Margin, Return on Assets), solvency/capital adequacy (e.g., Capital Adequacy Ratio), and asset quality (e.g., Gross Non-Performing Assets ratio). Following a traditional trend analysis and benchmark comparison against peer banks in the Indian landscape, the study will delve into advanced analytics. ML models, specifically powerful ensemble techniques like Random Forest and XGBoost, will be meticulously applied to identify the most influential ratios and underlying financial factors that significantly impact the bank's core profitability metrics and asset quality, thereby uncovering previously hidden or less obvious relationships and drivers. Furthermore, to address the critical need for forward-looking insights, Deep Learning models, particularly Long Short-Term Memory (LSTM) networks, will be developed and deployed for forecasting crucial future financial metrics. These LSTMs are uniquely capable of capturing intricate temporal dependencies, seasonal patterns (ee.g., quarter-on-quarter variations in credit growth or deposit mobilization), and market volatilities that profoundly affect banking operations. The performance of these AI-driven forecasting models will be rigorously evaluated against traditional linear time-series models using metrics such as Mean Squared Error (MSE) and prediction accuracy, with the expectation of demonstrating superior predictive power. Ultimately, this research aims to provide Bank of Baroda's stakeholders – including management, regulators, and investors – with more robust, dynamic, and datadriven insights, enhancing strategic decision-making capabilities, optimizing risk management frameworks, and fostering greater financial stability in a complex and evolving banking environment

Keywords :

Author : R.Gowthami,K.Lakshmi

Title : FINANCIAL STATEMENT ANALYSIS OF BANK OF BARODA

Volume/Issue : 2025;02(05(1))

Page No : 39-44

This study proposes an innovative and in-depth financial statement analysis of Punjab National Bank (PNB), a prominent public sector bank in India, by synergistically integrating traditional financial ratio analysis with advanced Machine Learning (ML) and Deep Learning (DL) techniques. Recognizing the complex and dynamic nature of the Indian banking sector, characterized by evolving credit cycles, stringent regulatory frameworks, and intense competition, conventional financial analysis often provides a retrospective view. This research aims to move beyond static analysis by leveraging the power of AI to unearth deeper insights and generate predictive intelligence.The methodology will involve meticulously collecting and processing PNB's audited financial statements over a significant 5-10 year period (e.g., FY2015-FY2024). A comprehensive set of bank-specific financial ratios will be computed across key dimensions including liquidity (e.g., Credit-Deposit Ratio, Liquid Assets to Total Assets), profitability (e.g., Net Interest Margin, Return on Assets, Cost-toIncome Ratio), solvency/capital adequacy (e.g., Capital Adequacy Ratio), and asset quality (e.g., Gross Non-Performing Assets Ratio, Provision Coverage Ratio).Subsequently, ML algorithms such as Random Forest and XGBoost will be employed. These models are adept at identifying intricate, non-linear relationships and will be used to pinpoint the most influential ratios impacting PNB's core profitability and asset quality, thereby revealing hidden drivers and potential risk factors. Furthermore, to provide crucial forward-looking perspectives, Long Short-Term Memory (LSTM) networks, a specialized form of Deep Learning, will be applied. LSTMs are particularly well-suited for time-series forecasting, enabling the models to capture inherent temporal dependencies, seasonal patterns (e.g., quarterly fluctuations in deposit growth or credit off-take), and market volatilities unique to the banking sector. The performance of these AI-driven forecasting models will be rigorously evaluated against traditional linear time-series models (e.g., ARIMA) using standard metrics like Mean Squared Error (MSE) and prediction accuracy. The expected outcome is to demonstrate how AI significantly enhances predictive accuracy and offers dynamic, datadriven insights, thereby empowering stakeholders with superior tools for strategic decisionmaking, proactive risk management, and more informed capital allocation within the complex banking landscape.

Keywords :

Author : Dr.A.Anil Kumar Reddy,K.Vanajakshi,M.Rohitha

Title : FINANCIAL STATEMENT ANALYSIS OF PNB

Volume/Issue : 2025;02(05(1))

Page No : 45-50

This study delves into the evolution of Working Capital Management (WCM) strategies by integrating traditional financial methodologies with advanced Machine Learning (ML) and Deep Learning (DL) techniques. Recognizing the critical role of efficient WCM in ensuring a firm's liquidity, profitability, and sustainable growth, especially within the context of seasonal fluctuations, supply chain complexities, and evolving economic landscapes in India, this research aims to provide a comprehensive framework for optimizing working capital. The study will first establish a baseline using conventional WCM approaches, focusing on the management of cash, inventory, accounts receivable, and accounts payable, and their impact on the Cash Conversion Cycle (CCC). It will then explore how ML algorithms, such as Random Forest and Gradient Boosting, can be applied to large historical datasets to identify the most significant internal and external factors influencing working capital needs, thereby improving forecasting accuracy for key components like sales demand, inventory levels, and payment patterns. Furthermore, Deep Learning models, particularly Long Short-Term Memory (LSTM) networks, will be deployed to capture complex temporal dependencies and non-linear relationships in highly volatile financial data, enabling more precise, real-time cash flow and working capital requirement predictions. The performance of these AI-driven models will be rigorously evaluated against traditional forecasting methods (e.g., ARIMA, regression analysis) using metrics like Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE). Ultimately, this research seeks to demonstrate how the synergy between established WCM principles and cutting-edge AI technologies can lead to superior liquidity management, reduced financing costs, minimized stockouts or excess inventory, and enhanced overall financial resilience for businesses in India.

Keywords :

Author : Dr.M.Ramakanth Reddy,R.Srilekha,Mallani Niharika

Title : WORKING CAPITAL MANAGEMENT STARTEGIES

Volume/Issue : 2025;02(05(1))

Page No : 51-56