Journal of Science Engineering Technology and Management Science

The increasing integration of renewable energy sources in microgrid systems necessitates efficient and high-quality power conversion. This paper presents a novel 31-level multilevel inverter (MLI) topology for standalone microgrid applications powered by a hybrid wind-photovoltaic (PV) system. The proposed MLI is designed with a minimal number of switches, reducing complexity, switching losses, and overall system cost while achieving high output voltage levels with lower total harmonic distortion (THD). PI conteoller is implemented to enhance the performance of the inverter, ensuring dynamic adaptability to variations in renewable energy generation and load conditions. Compared to traditional PI controllers, the FLC-based control strategy provides superior voltage regulation, rapid response, and improved system stability. The high-level output waveform of the proposed inverter significantly enhances power quality, reducing the need for bulky filters. Simulation and experimental validation confirm that the proposed 31-level inverter effectively integrates wind and PV sources while delivering high-efficiency and distortion-free power suitable for standalone microgrid applications. The results demonstrate improved power quality, lower THD, and enhanced system reliability, making it a promising solution for sustainable energy-based microgrids

Keywords : Multilevel inverter (MLI), 31-level inverter, Wind-PV hybrid system, Minimal switches, Standalone microgrid, Total Harmonic Distortion (THD), Power quality

Author : MR.K. GIRINATH,MR.CH SRISAILAM,S. HARINI,Y. RAKESH,K. MANIKANTA

Title : A 31-LEVEL WIND-PV BASED MULTILEVEL INVERTER WITH REDUCED SWITCH COUNT FOR STANDALONE MICROGRID APPLICATIONS

Volume/Issue : 2025;02(06)

Page No : 199-206

The growing use of solar energy has created a need for effective monitoring systems to ensure maintenance and optimal performance. This project presents the design and implementation of an IoT and microcontroller-based solar panel monitoring system that enables remote monitoring and management of parameters like voltage, current, temperature, and power output. Featuring real-time data collection, the system uses a microcontroller to interface with sensors and transmit data wirelessly to a cloud platform. By leveraging IoT technologies, it ensures seamless communication between solar panels and users. The project details system design, hardware, sensor integration, communication protocols, and software. Experimental results confirm the system’s effectiveness in tracking performance, detecting issues, and improving energy efficiency. Its scalability, flexibility, and costeffectiveness make it suitable for commercial, industrial, and residential solar applications. In addition, the system facilitates predictive maintenance by identifying anomalies early. This approach enhances the lifespan and reliability of solar power systems.

Keywords :

Author : MR.G RANGA PURUSHOTHAM,DR.P. PARTHASARADHY,VUNDYALA SAI PRASANNA,KOTTAWAR HARIHAR,VANAPARTHI MAHESH

Title : DESIGN OF SOLAR PANEL MONITORING SYSTEM USING CONTROLLER &IOT

Volume/Issue : 2025;02(06)

Page No : 207-210

Two innovative technologies, automated dripping irrigation systems and solar tracking systems, are pivotal in promoting efficient resource utilization and sustainable development The efficient utilization of water resources is crucial in agricultural practices, particularly in regions facing water scarcity. Drip irrigation systems have emerged as a sustainable solution to optimize water usage in agriculture. However, conventional drip irrigation systems often suffer from inefficiencies due to static positioning of the irrigation components, leading to uneven water distribution and wastage. This is an innovative approach to address these challenges by integrating a solar tracking system with automated drip irrigation technology. The system proposed adjusts the position of solar panels dynamically to optimize energy capture throughout the day. This ensures a consistent power supply to the drip irrigation system. Moreover, sensors and actuators are integrated into the irrigation components for real-time monitoring and control of water distribution, which is based on soil moisture levels. By merging solar tracking technology with automated drip irrigation, the system aims to improve water efficiency, decrease energy dependency, and optimize crop yields

Keywords :

Author : MRS.CH LAXMI,MR.M SURYAKANTH,P. VISHNUVARDHA,M.HARSHAVARDHAN,N. RAJKUMAR

Title : SOLAR POWERED MECHANIZED DRIP IRRIGATION

Volume/Issue : 2025;02(06)

Page No : 211-214

This paper presents solar based electric vehicle (EV) charging circuit. Incremental Conductance MPPT Algorithm is used to extract maximum power from the solar PV at STC conditions. A battery of rating 100AH is charged with the solar PV panel using a boost converter which generates output voltage of 400V. Then the voltage is stepped down for buck operation according to 220 V battery requirement. The SOC characteristic is observed to be fully charged within short period. The passive parameters (filter components on the input and output) of the system are derived and appropriately used in the work. Also in the absence of solar PV energy, electric vehicle is charged from the grid. A PR (proportional plus resonant) controller is used with a corner frequency of 10rad/sec. A 400 V dc output voltage is obtained through a H-bridge rectifier and applied to a DC-DC bidirectional converter. It is observed that the battery SOC is accomplished within a small period. During charging and discharging modes the battery voltage and current is presented. It is clear that the grid voltage and current are in phase during charging. During discharging they are said to be out of phase indicating the reverse power flow. IGBT switches are considered to be operating at 10 kHz. On-board electric vehicle chargers can be utilized at homes and parking places. The work reflects the usage of EV connected to solar exhibits less dependency on the grid with clean (zero emission) and smooth movement of the vehicle

Keywords : Battery, Electric vehicle, maximum power point, proportional resonant controller, State of Charge

Author : MR.S. RAJENDER REDDY,MR.S. PRAVEEN KUMAR,BAYYA BHAVANA,BOLLA SHEELA,KARNAM VIVEK

Title : SOLAR ENERGY BASED G2V AND V2G CHARGING INFRASTRUCTURE

Volume/Issue : 2025;02(06)

Page No : 215-222

The use of solar energy has increased significantly over the world. They are well-liked due to their endlessness and purity. It also stands out for being low maintenance. Yet, ifa little issue with the panel or circuit is not identified promptly, it could cost a lot to maintain. Another challenging task is finding the flaw inside the vast solar field. This study examines the viability of employing IOT for realtime fault detection. Reducing the maintenance expense and detection time, Panel temperature, light intensity, and current are monitored and maintained continuously, respectively, using temperature, light, and current sensors. In the proposed study to maintain the standard level of voltage, battery voltage is constantly monitored to meet the industrial need and to increase the life span. The study also aims to measure efficiency concerning the increase and decrease in power levels. Further, the study involves a cleaning system that can be integrated into the solar panel to clean the dust layer accumulated on the panel. Cleaning dust is an important factor in solar panel maintenance to improve efficiency and reduce corrosion. The novelty of the system lies in the comprehensive approach towards solar panel maintenance through the integration of IoT technology, smart cleaning systems, and rigorous analysis of efficiency factors

Keywords :

Author : MR.S PRAVEEN KUMAR,MS.G ANNAPURNAMM,G. SUDHAKAR,D. SOWMITH,G. SAI KUMAR

Title : SMART SOLAR PANEL MONITORING SYSTEM FOR REAL-TIME PERFORMANCE AND ENERGY OPTIMIZATION

Volume/Issue : 2025;02(06)

Page No : 223-227

Environmental concerns have garnered widespread attention, but electricity consumption continues to contribute to environmental pollution. To effectively conserve energy, users must have a clear understanding of individual appliance consumption. Existing energy feedback systems often present technical data that is inaccessible to most users. The most efficient approach to address environmental concerns associated with electricity consumption is by minimizing usage. This challenge is addressed through the creation of the Smart Energy Consumption Monitoring System. It enables users to manage power consumption within their building, providing real-time insights into electricity usage and automatically generating consumption reports. The system is designed to enhance the comfort, security, and energy efficiency of modern homes. The fundamental elements of this system consist of the microcontroller, which serves as the central hub for controlling temperature, light intensity, and motion detection. Multiple sensors, including temperature sensors, light sensors, and motion detectors, are strategically placed throughout the home to monitor and respond to environmental changes. The controller orchestrates the data from these sensors, allowing homeowners to remotely control temperature settings, adjust lighting levels, and receive real-time alerts on detected motion. This level of automation not only increases convenience but also enhances security by deterring potential intruders through intelligent lighting and motion-activated alerts. The proposed energy detection device utilizes an controller and various sensors like the ACS712, electric meter, and Wi-Fi connectivity. Collected data is analysed using the Internet of Things technology, facilitating seamless power consumption monitoring and management from anywhere, at any time

Keywords :

Author : MS.G ANNAPURNAMMA,MRS.R TEJASWI,BODASHEKHAR,GAVVA SAI KUMAR REDDY,KOUROJU MANITEJA

Title : WIRELESS HOME CONTROLBY BLUETOOTH LOW ENERGY TECHNOLOGY

Volume/Issue : 2025;02(06)

Page No : 228-232

The paper outlines a paradigm-breaking adaptive navigation system that redefines conventional mobility aid through intelligent multimodal interaction paradigms. Our research establishes a new paradigm in the integration of acoustic pattern recognition and tactile interface mechanisms to facilitate an autonomous personal transportation system. The system employs embedded computational intelligence to translate human linguistic patterns and analog control signals into synchronized mechanical outputs through the use of dedicated actuation circuits and rotational drive mechanisms. The acoustic interface eliminates physical contact requirements for motorimpaired users, with the integrated tactile control system providing redundant operating paths for enhanced system reliability. Our design prefers adaptive user experience, sustainable energy consumption, and real-time response ability, with ambient energy capture technologies implemented to facilitate operational autonomy. Experimental verification establishes enhanced functionality in acoustically controlled environments, with measured performance variations dependent upon speech pattern quality and environmental audio interference. This paper establishes new standards for independence enhancement and mobility optimization in assistive technology applications.

Keywords : Embedded systems, acoustic recognition, adaptive interfaces, personal mobility, accessibility technology

Author : N. Sahasra, Ch.Vaishnavi, N. Niharika, Ms.K.Padmaleela

Title : ADAPTIVE MULTIMODAL NAVIGATION FRAMEWORK FOR AUTONOMOUS PERSONAL MOBILITY ENHANCEMENT

Volume/Issue : 2025;02(06)

Page No : 233-237

???? ??? ?????? ???????? ??????? ?? ?? ????????? ???????? ??????? ????????? ?? ????????? ??????? ??????? ?? ?????? ??? ??? ????????? ????? ?????? ????, ???? ????? ?? ?????? ???? ??? ???? ??, ????? ?? ?????? ??????? ?????? ?? ???? ??????? ??? ?? ???? ???? ?????? ??????? ??? ???????? ???? ??? ????????? ?? ?????? ?? ??????? ????????, ???? ???????????? ?? ?????? ?????? ??????? ?? ???? ?? ?? ???????? ????????? ?????? ???? ??? ?? ?????? ??? ????????? ????? ?????? ???? ?? ???????, ???????????, ??????? ??????? ?? ??????? ?????? ?? ???????? ???? ??? ??? ?????? ??? 2020 ?? 2025 ?? ?? ???? ?? ???? ????? ?????? ???????? ?? ???????? ???? ??? ??? ??? ??, ?????????? ?? ????? ?? ?????????? ????? ?? ???????? ??? ?? ????

Keywords :

Author : ??. ???????? ????? ???? (????? ?????????? ???????)

Title : ????????? ????? ?????? ????: ?? ????????????? ??????

Volume/Issue : 2025;02(06)

Page No : 238-241

The impact of static versus animated ads in raising business literacy among young people in Chandrapur is examined in this study. Data were gathered from 200 respondents, ages 16 to 25, using a structured questionnaire and a descriptive study approach. The results show that when it comes to enhancing understanding, engagement, and recall of fundamental business concepts, animated ads perform noticeably better than static ones. Because of its clarity and aesthetic appeal, animated advertisements were favoured by most participants. The study highlights animation media's potential as a tactical teaching tool to promote business literacy among young people

Keywords : Animated advertisements, static advertisements, business literacy, youth engagement, Chandrapur, advertising effectiveness, visual communication, etc

Author : Shubham Shamsundar Bele, Dr. J. N. Chakravorty

Title : COMPARING THE EFFECTIVENESS OF STATIC VS ANIMATED ADVERTISEMENTS IN ENHANCING YOUTH BUSINESS LITERACY IN CHANDRAPUR

Volume/Issue : 2025;02(06)

Page No : 242-248

Phishing is an internet scam in which an attacker sends out fake messages that look to come from a trusted source. A URL or file will be included in the mail, which when clicked will steal personal information or infect a computer with a virus. Traditionally, phishing attempts were carried out through wide-scale spam campaigns that targeted broad groups of people indiscriminately. The goal was to get as many people to click on a link or open an infected file as possible. There are various approaches to detect this type of attack. One of the approaches is machine learning. The URL’s received by the user will be given input to the machine learning model then the algorithm will process the input and display the output whether it is phishing or legitimate. There are various ML algorithms like SVM, Neural Networks, Random Forest, Decision Tree, XG boost etc. that can be used to classify these URLs. The proposed approach deals with the Random Forest, Decision Tree classifiers. The proposed approach effectively classified the Phishing and Legitimate URLs with an accuracy of 87.0% and 82.4% for Random Forest and decision tree classifiers respectively

Keywords :

Author : A.Sushmitha, P. Akhila, D. Manasa, B. Pavani, S. Anusha

Title : Phishing Website Detection By Using ML

Volume/Issue : 2025;02(06)

Page No : 249-255

Rice is one of the major cultivated crops in India which is affected by various diseases at various stages of its cultivation. It is very difficult for the farmers to manually identify these diseases accurately with their limited knowledge. Recent developments in Deep Learning show that Automatic Image Recognition systems using Convolutional Neural Network (CNN) models can be very beneficial in such problems. Since rice leaf disease image dataset is not easily available, we have created our own dataset which is small in size hence we have used Transfer Learning to develop our deep learning model. The proposed CNN architecture is based on VGG-16 and is trained and tested on the dataset collected from rice fields and the internet. The accuracy of the proposed model is 92.46%.

Keywords :

Author : P.Narasimha, V. Manichandhana, R. Harshini, K. Manosri, V. Anjali, B. Krupamani

Title : RICE LEAF DISEASE CLASSIFICATION

Volume/Issue : 2025;02(06)

Page No : 256-263

The exponential rise of short-form videos on platforms like YouTube Shorts, TikTok, and Instagram Reels has led to increased concern over the spread of hate speech, often hidden in the audio tracks of these videos. Traditional text-based detection methods fail to capture the nuances of spoken content. This project proposes an audio-based hate speech classification system using deep learning techniques that analyze speech patterns, tone, and content from video audio. By leveraging audio preprocessing, feature extraction (e.g., MFCCs), and classification models such as LSTM and CNN, the system can identify hate speech even in disguised or nuanced speech forms. This model offers a scalable and automated solution to moderate content effectively on social media platforms.

Keywords :

Author : Karuna Sree, K.Suchithra, D.Srilekha,S G.Gowthami, S.Sindhu, A.Vijaya Laxmi

Title : AUDIO BASED HATE SPEECH CLASSIFICATION FROM ONLINE SHORT FORM VIDEOS

Volume/Issue : 2025;02(06)

Page No : 264-274

In the digital era, the integration of artificial intelligence (AI) into education has revolutionized how knowledge is delivered, managed, and accessed. EDUBOT is a smart AI-powered chatbot designed for educational institutions to streamline the dissemination and management of academic knowledge. By leveraging natural language processing (NLP) and machine learning, EDUBOT interacts with users in a human-like manner, providing instant responses to academic queries, guiding users through complex educational resources, and supporting institutional knowledge repositories. This project focuses on the development and implementation of EDUBOT as a 24/7 virtual assistant capable of handling FAQs, providing academic material, and assisting in administrative tasks, thereby improving educational efficiency and access to information.

Keywords :

Author : G. Vinoda, R.Maneesha, G.Sathwika, G.Keerthana, T.Sreeja, A.Bhanu Sri

Title : EDUBOT - AN AI SMART CHATBOT FOR KNOWLEDGE MANAGEMENT SYSTEM

Volume/Issue : 2025;02(06)

Page No : 275-282

ML has contributed towards opening up new frontiers in several sectors including health and medical facilities. Multiple ML approaches has been designed and developed to execute prediction oriented analysis on big data acquired from several devices. Performing analysis through prediction is critical and daunting yet eventually it can aid and assist medical professionals and healthcare providers to arrive at strategic and wise assessments that could prove to be effective during prognosis as well as diagnosis at the time of patients’ treatments. This study takes into account the notion of analysis based on prediction especially in healthcare domain where ML algorithms are utilized to perform the necessary research. To validate and evaluate our proposed research, a training dataset comprising of patient’s health records are acquired and 6 diverse ML algorithms are employed on it.Analysis of performance and effectiveness of the ML algorithms and their comparative efficiency in prediction of diabetes has been elaborated and discussed in detail. Evaluation of the various ML approaches helps towards understanding the suitability of reliable ML algorithm that could be utilized for predicting diabetes and the associated symptoms. This study is thus aimed at assisting medical practitioners and health personnel to detect the diabetes earlier through application of appropriate ML methods. These algorithms utilised are artificial neural networks(ANN) , XG boosting ,Ada boosting, K Nearest Neighbours (KNN), Support Vector Machine (SVM), Decision Tree (DT).Through comparing and validating the above mentioned machine learning techniques facilitates the prediction of diabetes by means of an application where the users can enter the relevant details and acquire prediction based results. This is an open access a

Keywords :

Author : J.Santosh Kumar, P.Ankitha, V.Sravya, Ch.Mounika, P.Shikhamani, R.Sravani

Title : MACHINE LEARNING BASED DIABETICS PREDICTION USING WITH AWS CLOUD

Volume/Issue : 2025;02(06)

Page No : 283-290

Cash management is a critical function within financial institutions, ensuring optimal liquidity, efficient fund allocation, and secure transaction processing. Traditional cash management systems often rely on static rule-based frameworks and manual interventions, which limit their ability to handle real-time financial complexities, forecast cash flows accurately, and detect anomalies or fraud. With the increasing volume, velocity, and variety of financial data, there is a growing need for intelligent systems that can adapt, predict, and automate cash management processes. This study explores how Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) can be leveraged to build smarter, data-driven cash management systems. AI algorithms are used for real-time decision-making in cash forecasting, liquidity risk assessment, and transaction prioritization. ML models, such as Random Forest and Gradient Boosting, are employed to predict cash inflows and outflows based on historical patterns, business cycles, and external economic indicators. DL models, particularly Long Short-Term Memory (LSTM) networks, are utilized for sequence prediction in time-series financial data, enhancing the accuracy of cash flow forecasting. Additionally, anomaly detection techniques are integrated to identify potential fraud or operational errors, ensuring system integrity and compliance.By combining these intelligent technologies, the proposed system enhances operational efficiency, reduces human error, and improves financial planning accuracy. This AIdriven framework represents a transformative step toward building fully automated, adaptive, and secure cash management systems that align with the dynamic needs of modern financial institutions.

Keywords :

Author : D.Swetha, Ragiri Manisha, R.Srilekha

Title : CASH MANAGEMENT SYSTEM

Volume/Issue : 2025;02(06)

Page No : 291-298

The study titled “A Study of Various Vehicle Loans Provided by HDFC Bank in Nagpur” aims to analyze the different vehicle loan schemes offered by HDFC Bank and their impact on customer satisfaction, accessibility, and financial convenience for borrowers in the Nagpur region. Vehicle loans have become an essential financial product for middle-class and upper-middle-class families in India, enabling individuals to fulfill their aspiration of owning personal vehicles without immediate financial burden. This study focuses on understanding the features of HDFC Bank’s vehicle loan portfolio, including interest rates, loan tenure, processing charges, eligibility criteria, repayment options, and customer service quality. The research highlights that HDFC Bank offers competitive vehicle loan products with flexible repayment structures and attractive interest rates compared to other private and public sector banks. The study also evaluates the level of awareness among Nagpur customers regarding loan schemes, their decision-making factors, and the challenges faced during the loan application and disbursement process. Findings suggest that while customers appreciate the quick processing and digital facilities offered by HDFC Bank, some concerns remain regarding hidden charges, complex documentation, and high prepayment penalties. The study emphasizes the role of customer relationship management, transparency in communication, and financial literacy in enhancing customer trust and satisfaction. Overall, this research contributes to understanding customer perceptions of vehicle loans in Nagpur and provides insights into how HDFC Bank can further improve its loan services to remain competitive in the retail banking sector. The study concludes that effective loan structuring, customer-centric policies, and innovative digital solutions are crucial for strengthening HDFC Bank’s position in the vehicle loan market of Nagpur.

Keywords :

Author : D. Keerthi Ganesh Reddy, V.Sandeep Kumar, K.Archana

Title : A STUDY OF VARIOUS VEHICLE LOAN PROVIDE BY HDFC BANK IN NAGPUR

Volume/Issue : 2025;02(06)

Page No : 299-306

The stock market is a complex, dynamic system influenced by numerous factors including economic indicators, sector performance, and investor behavior. Traditional analysis methods often fall short in capturing intricate patterns and predicting stock price movements accurately. This study employs Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques to perform a comparative analysis of share price trends across various industry sectors. By leveraging historical stock data, news sentiment, and macroeconomic variables, the study aims to develop robust predictive models that can identify sector-specific price movements and market behavior .Machine learning algorithms such as Random Forest, Support Vector Machines (SVM), and Gradient Boosting are utilized to analyze large volumes of structured financial data, uncovering hidden patterns and relationships among different sectors. Deep learning models, including Long Short-Term Memory (LSTM) networks, are applied for time-series forecasting to capture the sequential dependencies in stock prices. The integration of Natural Language Processing (NLP) techniques further enriches the analysis by incorporating market sentiment from news and social media, providing a comprehensive view of factors impacting share prices.The findings of this study are expected to assist investors, portfolio managers, and financial analysts in making informed decisions by providing sector-wise comparative insights and accurate share price predictions. Additionally, the research demonstrates the potential of AI-driven approaches in enhancing traditional financial analysis, offering scalable and adaptive tools for the evolving landscape of stock market investment.

Keywords :

Author : D. Nandini,M.Rajeshwar Reddy, R.Gowthami

Title : A STUDY ON COMPARATIVE ANALYSIS OF SHAREPRICE IN VARIOUS SECTOR

Volume/Issue : 2025;02(06)

Page No : 307-315

The rapid adoption of electronic banking (e-banking) services has transformed the banking sector, providing customers with convenient, efficient, and secure ways to conduct financial transactions. However, the level of consumer awareness and the factors influencing the adoption of these digital services vary significantly across different demographic groups. This study leverages Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) techniques to analyze consumer awareness, behavior, and satisfaction regarding e-banking services offered by Union Bank.Using survey data combined with transactional and interaction logs, machine learning models such as decision trees and support vector machines are employed to classify consumers based on their awareness levels and usage patterns. Deep learning models, particularly neural networks, analyze complex behavioral data to uncover latent factors that influence e-banking adoption and usage. Additionally, Natural Language Processing (NLP) techniques are applied to customer feedback and social media to gauge sentiment and identify common concerns or barriers faced by consumers.The insights generated from this study aim to help Union Bank tailor its marketing strategies, enhance user education, and improve e-banking services to increase adoption rates and customer satisfaction. Moreover, the research demonstrates the potential of AI-driven analytics in understanding consumer behavior in the rapidly evolving digital banking landscape.

Keywords :

Author : E.Praveena, K.Archana Bhargavi, R.Manisha

Title : A STUDY ON CONSUMER AWARENESS ON E-BANKING SERVICE AT UNION BANK

Volume/Issue : 2025;02(06)

Page No : 316-324

The home loan sector plays a vital role in promoting housing development and financial inclusion in India. HDFC Bank, as one of the leading financial institutions, offers a variety of home loan schemes tailored to meet the needs of different customer segments. This study investigates the performance and effectiveness of HDFC Bank’s home loan services by integrating advanced Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) approaches to better understand consumer behavior, loan approval trends, risk prediction, and customer satisfaction .By leveraging real-world data—such as loan applications, credit scores, income levels, and repayment history—this research applies machine learning algorithms like decision trees, logistic regression, and random forests to identify the most influential factors affecting home loan approvals. Deep learning models, particularly neural networks, are also implemented to handle more complex relationships and predict defaults with higher accuracy. Sentiment analysis using Natural Language Processing (NLP) is applied to customer reviews and feedback, helping to understand public perception of HDFC’s home loan services.The findings aim to assist HDFC Bank in optimizing its loan processing workflows, improving customer targeting, and enhancing risk management through automation and data-driven insights. The study demonstrates how AI, ML, and DL can bring precision, speed, and intelligence to the home loan segment, ensuring better service delivery and customer satisfaction.

Keywords :

Author : E.Praveen Kumar, M.Rajeshwar Reddy, R.Gowthami

Title : STUDY OF HOME LOAD AT HDFC BANK

Volume/Issue : 2025;02(06)

Page No : 325-333

The life insurance sector in India is undergoing rapid digital transformation, with institutions like Kotak Mahindra Bank integrating advanced technologies to improve customer experience, risk assessment, and product personalization. This study presents an AI, Machine Learning (ML), and Deep Learning (DL)-based analytical exploration of Kotak Mahindra’s life insurance offerings, focusing on how datadriven strategies can optimize policy performance, customer acquisition, and satisfaction. Using a combination of historical policyholder data, claim records, and customer feedback, the study employs ML algorithms such as Random Forest, Logistic Regression, and K-Means Clustering to predict policy renewal behavior, assess risk levels, and segment customers based on demographics and buying behavior. Natural Language Processing (NLP) is used to analyze unstructured data such as customer reviews and support interactions, revealing key emotional drivers influencing insurance purchases. LSTM networks and other deep learning models are utilized to forecast claim patterns, retention trends, and customer lifetime value. The results indicate that AI-powered approaches significantly enhance decision-making in life insurance services. Predictive analytics help reduce churn, optimize underwriting processes, and recommend personalized insurance plans. This study demonstrates that by leveraging intelligent systems, Kotak Mahindra Bank can deliver smarter, more responsive, and customer-centric life insurance solutions in an increasingly competitive financial landscape.

Keywords :

Author : G .Pavani, M.Rajeshwar Reddy, R.Gowthami

Title : A STUDY ON LIFE INSURANCE OF KOTAK MAHINDRA BANK

Volume/Issue : 2025;02(06)

Page No : 334-343

Cash management plays a pivotal role in the financial health and operational stability of organizations. It involves the systematic planning, monitoring, and optimization of cash inflows and outflows to ensure sufficient liquidity while maximizing returns on idle cash. In the context of increasing financial complexity and volatility, traditional cash management approaches are no longer sufficient. This study explores the integration of Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) into annual cash management systems to enhance efficiency, accuracy, and foresight. Using historical financial transaction data from annual records, the study leverages ML algorithms such as Random Forest, Decision Trees, and XGBoost to forecast future cash flow patterns. These models help identify peak expenditure periods, potential cash shortages, and optimal investment windows. Deep Learning models, particularly Recurrent Neural Networks (RNNs) and LSTMs (Long ShortTerm Memory), are used to capture time-dependent patterns and seasonal fluctuations in cash behavior. Furthermore, AI-driven dashboards and anomaly detection systems are introduced to alert financial managers in real time about irregularities in cash movements or deviations from forecasts. By combining AI, ML, and DL, this study provides a smart, data-driven framework for annual cash management, enabling organizations to make proactive and informed financial decisions. The results demonstrate that intelligent forecasting and automation significantly improve liquidity planning, reduce manual errors, and increase transparency in cash operations. This approach not only optimizes working capital but also strengthens overall financial control and risk management in modern institutions.

Keywords :

Author : K. Shirisha, M.Rajeshwar Reddy, R.Gowthami

Title : CASH MANAGEMENT OF ANNUAL

Volume/Issue : 2025;02(06)

Page No : 344-353

The digital advertising ecosystem has undergone a radical transformation with the advent of advanced computational technologies. Consumer attitudes, once relatively passive in response to traditional advertising, have evolved dramatically in today’s hyper connected environment. This research delves deep into the complexities of consumer attitudes toward online advertising in an era increasingly shaped by artificial intelligence, machine learning (ML), and deep learning (DL). Consumers interact with a multitude of ads across platforms like Google, Facebook, Instagram, YouTube, and e-commerce websites, often without consciously engaging. As online advertising grows more data-driven and algorithmically optimized, this study seeks to understand the factors shaping consumer responses—ranging from perceived utility, relevance, trust, to privacy concerns and emotional reactions. Incorporating AI techniques, the study uses natural language processing (NLP), user clustering, predictive modeling, and neural network sentiment analysis to dissect consumer sentiments and behavioral tendencies. It highlights how ML and DL enable the personalization of ad experiences and how these same technologies can be employed to measure, predict, and ethically guide consumer engagement. By evaluating largescale datasets and consumer interviews, the study not only reveals patterns of ad acceptance and avoidance but also proposes a roadmap for responsible AI integration in digital marketing. This multidisciplinary research provides critical insights for businesses, marketers, technologists, and policymakers striving to balance innovation, consumer satisfaction, and digital ethics in advertising

Keywords :

Author : K.Sai Divya, K.Shashidhar, R.Manisha

Title : CONSUMER ATTITUDE TOWARDS ONLINE ADVERTISING

Volume/Issue : 2025;02(06)

Page No : 354-361

The foreign exchange (forex or FX) market, being the world’s largest and most liquid financial marketplace, plays a pivotal role in global economic stability and investment activity. With the daily trading volume exceeding $6 trillion, understanding forex market strategies is crucial for investors, institutions, and policymakers. This research delves into traditional and modern forex strategies—technical analysis, fundamental analysis, carry trade, momentum-based trading—and integrates these with cuttingedge machine learning (ML) and deep learning (DL) models to enhance predictability and decision-making. The paper explores the evolution of forex strategies, highlights the impact of AI-powered forecasting models, and investigates the role of macroeconomic factors, geopolitical events, and investor sentiment in shaping currency fluctuations. Utilizing real-time data, neural networks, and sentiment analysis tools, this study bridges finance and software intelligence to create a robust decision-support framework. The findings provide a strategic roadmap for leveraging algorithmic and AI-driven methods to manage risks and capitalize on opportunities in volatile currency markets

Keywords :

Author : K.Subash, R.Gowthami

Title : FOREIGN EXCHANGE MARKET STRATEGIES

Volume/Issue : 2025;02(06)

Page No : 362-370

This research investigates the comparative financial performance of State Bank of India (SBI) and Housing Development Finance Corporation (HDFC) Bank, two major players in India's banking sector. Over a five-year span, this study examines key financial indicators such as profitability, efficiency, liquidity, and solvency. More importantly, the research integrates modern software-driven techniques, including machine learning (ML) and deep learning (DL), to identify trends, forecast risks, and evaluate performance with higher precision. The methodology includes traditional ratio analysis, ML classification models, and DL time-series prediction tools such as LSTM. The results demonstrate that while SBI's asset base provides stability, HDFC's lean operational model delivers stronger returns. The paper also highlights how AI can be used not only to automate financial analysis but also to democratize insights for stakeholders, enabling a shift toward intelligent decision-making in modern finance. With the convergence of finance and software, this study contributes to both academic knowledge and practical financial intelligence. The ultimate aim is to empower banks, investors, and policymakers with proactive intelligence through datadriven, software-augmented financial performance evaluations

Keywords :

Author : M.Rajesh, V.Sandeep Kumar, K.Archana

Title : A STUDY ON FINANCIAL PERFORMANCE OF BANKS A COMPARATIVE ANALYSIS OF IDFC BANK

Volume/Issue : 2025;02(06)

Page No : 371-378