Journal of Science Engineering Technology and Management Science

AI-powered framework designed to summarize complex legal and financial documents using modern Natural Language Processing techniques. The system combines two advanced models, COLBERT and T5, to improve both the relevance and readability of generated summaries. COLBERT is used to understand the contextual meaning of the document and rank important sentences effectively, while T5 generates concise and meaningful abstractive summaries from the selected content. Unlike traditional extractive methods, this approach focuses on capturing the true intent of the text and expressing it in a simplified manner. The model was trained using a dataset consisting of legal and financial documents along with their summaries. Due to computational limitations in Google Collab, a smaller dataset was used, containing 2,000 training samples and 300 testing samples. Despite these constraints, the system achieved a Rouge-1 score of 30%, indicating promising performance. The results highlight that even with limited resources, transformer-based models can produce useful summaries for domain-specific texts. This framework offers a scalable and cost-effective solution, with potential for significant improvement when trained on larger datasets & powerful hardware.

Keywords : AI-powered summarization, Natural Language Processing, COLBERT, T5 transformer, abstractive summarization, legal documents, financial texts, contextual understanding, sentence ranking, Rouge score evaluation, deep learning, text generation.

Author : Bandi Pranavi, Charan, Geerish Chennale, Gulla Naresh, Mrs. Mercy Joycce

Title : An Automated Summarization Framework for Complex Financial and Legal Texts

Volume/Issue : 2026;03(05)

Page No : 370-375

During disaster search and rescue operations often hinder because of collapse building debris. Rescue team often suffer to reach victim on time which may cause death to victim. To easy search operations we are combining Robotic Hardware along with Machine Learning algorithms. Robots can easily have reached dangerous locations and then apply Machine Learning algorithm to detect presence of human or their body parts. During disaster ML algorithms must work accurately for human detection so we are employing CNN deep learning algorithm which is best known for optimize features extraction and this extracted feature will get trained with various ML algorithms such as Random Forest, SVM and Decision Tree. Each algorithm performance is evaluated in terms of Accuracy, Precision, Recall, Confusion Matrix and FSCORE. All algorithms able to get more than 90% accuracy on CNN optimized features. For accurate prediction Dataset will play an important role but on internet no such dataset exists so we downloaded some disaster images from internet which is created using Virtual Disaster. Dataset size was so small so we applied augmentation algorithm to increase dataset images count.

Keywords : Disaster search and rescue , Robotic hardware, Machine learning, Human detection, Convolutional Neural Network , Feature extraction, Random Forest, Support Vector Machine , Decision Tree, Data augmentation.

Author : G.Pravalika, D.Lakshmi Narasimha, G.Anand, S.Sai Reddy, Mr. S. Bavankumar

Title : AI-Enabled Disaster Prediction and Autonomous Search Operations Platform

Volume/Issue : 2026;03(05)

Page No : 376-381

Demand forecasting plays a crucial role in effective decision-making across industries such as retail, supply chain, and inventory management. This work presents a data-driven machine learning framework for predicting short-term and long-term product demand using multiple algorithms. The system is designed to compare the performance of traditional and advanced models, including Random Forest, Gradient Boosting, LSTM, and XGBoost. Initially, the dataset is pre-processed through normalization, shuffling, and splitting into training and testing sets to ensure reliable evaluation. Each model is trained on 80% of the data and tested on the remaining 20% to measure performance. The evaluation is conducted using metrics such as R² score for accuracy and Root Mean Square Error (RMSE) for prediction error analysis. Experimental results show that Random Forest and Gradient Boosting provide moderate accuracy, while LSTM captures temporal patterns more effectively. However, the XGBoost model outperforms all other methods by achieving the highest accuracy and lowest error rate. The system also includes a user interface that enables real-time demand prediction for selected products. The results demonstrate that advanced ensemble techniques can significantly enhance forecasting performance. This approach provides a reliable and efficient solution for demand prediction in real-world applications. The proposed system can support better planning, reduce uncertainty, and improve operational efficiency.

Keywords : Demand Forecasting, Machine Learning, XGBoost, Random Forest, Gradient Boosting, LSTM, Time Series Prediction, RMSE, R² Score

Author : H Sreeja, Akhil Reddy, Tharun Teja Rao, P Chandra Kashiyap, Dr. R. Santhoshkumar

Title : Machine Learning-Based Demand Forecasting for Short- and Long-Term Prediction

Volume/Issue : 2026;03(05)

Page No : 382-389

Human-machine interaction systems are growing more and more important in smart places like offices, schools, banks, and hospitals. This project shows an AI-based automatic greeting machine made with Arduino that greets visitors automatically based on the time of day and whether or not a person is there. An ultrasonic sensor is used by the system to find out when someone is getting close to it. A standard RT Clock (RTC) standard module is used to get the right time right now. The Arduino uses the time data to choose the best greeting message, like "Good Morning," "Good Afternoon," or "Good Evening." An LCD screen shows the chosen greeting, and the DF Mini Player component connected to a the speaker plays it at the same time. This automated greeting protocol cuts down on the need for the human receptionists and makes sure that everyone is polite and consistent. The suggested system is affordable, dependable, and works well in smart environments in real time.

Keywords :

Author : E Ashwinin, M Keerthi, R Abhiram, B Nikhitha, Mrs. K Swayam Prabha

Title : Automatic Greeting Machine Based on AI

Volume/Issue : 2026;03(05)

Page No : 390-397

Derivative trading has become an important component of the Indian capital market due to increasing financial innovation, market expansion, and the growing participation of investors in risk management and speculative activities. This study focuses on analyzing derivative trading in the Indian capital market by examining the role, growth, functions, and impact of derivative instruments such as futures, options, forwards, and swaps in financial market operations. The research aims to evaluate how derivative trading helps investors manage market risks, improve liquidity, increase market efficiency, and provide investment opportunities in the Indian financial system. Derivative instruments are widely used for hedging, speculation, arbitrage, and portfolio management purposes in stock exchanges such as the National Stock Exchange of India and Bombay Stock Exchange. The study also examines the influence of market volatility, investor behavior, regulatory policies, and technological advancements on derivative trading activities in India. The research is based on both primary and secondary data collected from investors, brokers, financial reports, journals, stock market publications, and online financial resources. The findings indicate that derivative trading significantly contributes to market liquidity, price discovery, risk management, and investment diversification in the Indian capital market. The study concludes that effective regulatory systems, technological development, investor awareness, and efficient trading mechanisms are essential for strengthening derivative trading practices and ensuring the stable growth of the Indian capital market.

Keywords : Derivative Trading, Indian Capital Market, Futures, Options, Forwards, Swaps, Risk Management, Hedging, Speculation, Arbitrage, Portfolio Management, Market Liquidity, Price Discovery, Market Volatility, Investor Behavior, Financial Innovation, Regulatory Policies, Investment Diversification, NSE, BSE

Author : Mrs.T.Naga Lakshmi, Rajineni Siva Krishna

Title : DERIVATIVE TRADING IN INDIAN CAPITAL MARKET

Volume/Issue : 2026;03(05)

Page No : 398-405

E-banking has emerged as one of the most significant innovations in the Indian banking sector due to rapid technological advancements, increasing internet penetration, smartphone usage, and digital financial services. This study focuses on analyzing the future trends and prospects of e-banking in India by examining how digital technologies are transforming banking operations, customer services, financial transactions, and banking accessibility. The research aims to evaluate various ebanking services such as internet banking, mobile banking, digital wallets, Unified Payments Interface (UPI), artificial intelligence, blockchain technology, cloud computing, and cybersecurity systems that are shaping the future of the banking industry in India. E-banking provides customers with convenient, secure, fast, and cost-effective banking services including online fund transfers, bill payments, digital transactions, account management, and financial services through electronic platforms. The study also examines the impact of government initiatives such as Digital India, financial inclusion programs, and cashless economy policies on the growth of ebanking services. The research is based on both primary and secondary data collected from customers, bank employees, journals, websites, banking reports, and financial publications. The findings indicate that technological innovation, digital payment systems, artificial intelligence, and customer-centric banking services significantly contribute to the growth and expansion of e-banking in India. The study concludes that future technological developments, improved cybersecurity measures, digital financial literacy, and advanced banking technologies will play a major role in strengthening customer satisfaction, operational efficiency, financial inclusion, and long-term growth prospects of e-banking in India.

Keywords :

Author : 1Dr. D.N.V.Krishna Reddy, 2 Sayyad Shajiya

Title : FUTURE TRENDS & PROSPECTS OF E-BANKING IN INDIA

Volume/Issue : 2026;03(05)

Page No : 406-416

The mutual fund industry plays an important role in the development of financial markets, investment opportunities, wealth creation, and economic growth. This study focuses on the growth of the mutual fund industry through a comparative study of India and the United States. Mutual funds help investors invest in diversified portfolios managed by professional fund managers, reducing investment risk and improving financial returns. The United States mutual fund industry is one of the largest and most developed financial markets in the world because of strong investor participation, advanced financial systems, diversified investment products, and high institutional involvement. In contrast, the Indian mutual fund industry is one of the fastest-growing financial sectors due to increasing financial literacy, digital investment platforms, Systematic Investment Plans (SIPs), rising middle-class income, and expanding retail investor participation. The study examines factors such as Assets Under Management (AUM), investor behavior, digital trading systems, regulatory frameworks, portfolio diversification, and market growth trends in both countries. Technological advancements and digital financial systems have significantly improved investment accessibility, online trading efficiency, and investor participation in mutual fund markets. The study concludes that mutual fund industry growth positively influences financial inclusion, capital market development, investment opportunities, economic stability, and long-term financial sustainability in both India and the United States.

Keywords :

Author : 1Mr. V. Suresh, 2 Siddini Venkata Ramana

Title : GROWTH IN MUTUAL FUND INDUSTRY A COMPARATIVE STUDY OF INDIA AND U.S. LITERATURE REVIEW

Volume/Issue : 2026;03(05)

Page No : 417-422

With the overwhelming amount of digital news available today, helping users discover relevant content has become increasingly important. This work proposes a personalized news recommendation system that combines contextual text understanding with graph-based learning. The model leverages the Microsoft MIND dataset to capture user reading patterns, including both interacted and ignored articles, along with rich news attributes such as category and textual content. To better understand the semantics of news articles, a pre-trained BERT model is used to generate meaningful text representations. These representations are then structured into a graph, where relationships between users and news items are modelled and refined through a Graph Convolutional Neural Network . By learning from these complex connections, the system is able to capture deeper patterns in user preferences. Compared to conventional approaches like LSTM and CNN, the proposed method demonstrates improved recommendation quality by effectively integrating relational and contextual information. The results highlight the model’s ability to deliver more accurate and personalized news suggestions, making it a promising solution for modern content recommendation systems.

Keywords :

Author : Mandala Srikaran, Ramagiri Vaman, Muthineni Abhinay, Karingula Ganesh, Mr. B. Karthik Anand

Title : Graph-Based Personalized News Recommendation Using Deep Contextual Embeddings

Volume/Issue : 2026;03(05)

Page No : 423-428

With the rapid growth of digital payments and online banking, detecting fraudulent transactions has become an important concern for financial organizations. Traditional detection methods often fail to identify fraud accurately due to the complex and evolving nature of fraudulent activities. This project presents an improved fraud detection system using the XGBoost machine learning algorithm, combined with Principal Component Analysis (PCA) to enhance feature selection and reduce data complexity. The model is developed and tested using a publicly available fraud transaction dataset from Kaggle. During implementation, various stages such as data preprocessing, feature extraction, model training, and evaluation are carried out systematically. The performance of the proposed model is assessed using key evaluation metrics including accuracy, precision, recall, and F1-score. To validate its effectiveness, the results are compared with the Naïve Bayes algorithm. The comparison shows that the XGBoost model performs significantly better in identifying fraudulent transactions, achieving accuracy above 99% along with improved precision and recall values. Additionally, the system is capable of predicting fraudulent activities in real-time using unseen test data. Overall, the results demonstrate that the proposed approach is efficient and reliable for detecting online transaction fraud, making it suitable for real-world financial applications.

Keywords :

Author : Belige Madhumitha, Jakkidi Bhavya Sri, Nagapuri Pranay, Janne Charan, Mr. G L Singh

Title : Detection of Fraudulent Online Transactions Using Machine Learning Techniques

Volume/Issue : 2026;03(05)

Page No : 429-434

There have been significant changes in the global luxury fashion industry owing to globalization, technological development, changing lifestyles of consumers, and heightened levels of societal consciousness. Today, luxury fashion consumption not only relates to its basic purpose but is also driven by its symbolic values, including prestige, self-expression, social position, and pleasure, among others. This paper analyzes the significance of symbolic value in influencing the behavior of luxury fashion consumption by bringing together relevant theoretical concepts, scholarly studies, and market trends. The review shows that luxury products are symbols of social and psychological nature through which the consumer conveys his/her identity. Based on well-known theories like conspicuous consumption, hedonic consumption, impression management, reference groups, and signaling theory, the paper highlights the multifaceted approach towards luxury consumption behavior. Nevertheless, there are also several important issues that arise from the literature review, among which include problems with measurements, market segmentation, and increasing presence of counterfeits and masstige products, which altogether make the study of symbolic luxury consumption quite problematic. The findings from the literature review reveal that future research should focus on creating culturally adaptive instruments for measuring luxury consumption behavior, further exploring virtual luxury spaces, and implementing more stringent policies.

Keywords : Luxury fashion consumption, symbolic value, consumer behaviour, prestige, social status, identity signaling, conspicuous consumption, hedonic consumption, cultural influence, digital luxury, social media.

Author : Jagadishwar Reddy REDDYGARI

Title : Understanding the Role of Symbolic Value in Shaping Luxury Fashion Consumption Patterns

Volume/Issue : 2026;03(05)

Page No : 434-441