Browsing by Author "Kumar, M.H."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Framework for Bank Loan Re-Payment Prediction and Income Prediction
    (Institute of Electrical and Electronics Engineers Inc., 2023) Dhruv, C.; Paul, D.; Kumar, M.H.; Anand Kumar, M.; Reddy, M.S.
    This research study aims to develop a predictive framework for income and bank loan repayment prediction. The primary objective is to accurately predict an individual's income and their ability to repay a loan to help them make informed financial decisions. Using a data-driven approach, we collected and analyzed data on various factors that impact income and loan repayment, such as employment history, education, credit score, and demographic information. This data will be used to build predictive models that can provide accurate estimates for both income and loan repayment. The models will be validated using historical data and refined to improve accuracy. The study will focus on developing two separate predictive models: one for income prediction and another for bank loan repayment prediction. The income prediction model will provide individuals with an estimate of their future income based on their individual financial circumstances. The bank loan repayment prediction model will help financial institutions predict the likelihood of loan repayment based on the borrower's financial history and current financial circumstances. This predictive framework will provide valuable insights into the financial stability of individuals and the creditworthiness of borrowers. It will help individuals plan for their financial future, such as saving for retirement or investing in the stock market. It will also assist financial institutions in making informed lending decisions, reducing the risk of loan defaults, and improving the overall health of the financial industry. The development of a predictive framework for income and bank loan repayment prediction will provide valuable insights and tools for both individuals and financial institutions. Accurate predictions of income and loan repayment will enable informed financial decisions, improving the financial stability and well-being of all parties involved. We have created a user-friendly financial bot that can provide basic definitions of financial terms based on user queries. © 2023 IEEE.
  • No Thumbnail Available
    Item
    scaLAR SemEval-2024 Task 1: Semantic Textual Relatednes for English
    (Association for Computational Linguistics (ACL), 2024) Kumar, M.H.; Anand Kumar, M.
    This study investigates Semantic Textual Related- ness (STR) within Natural Language Processing (NLP) through experiments conducted on a dataset from the SemEval-2024 STR task. The dataset comprises train instances with three features (PairID, Text, and Score) and test instances with two features (PairID and Text), where sentence pairs are separated by'/n' in the Text column. Using BERT(sentence transformers pipeline), we explore two approaches: one with fine-tuning (Track A: Supervised) and another without finetuning (Track B: UnSupervised). Fine-tuning the BERT pipeline yielded a Spearman correlation coefficient of 0.803, while without finetuning, a coefficient of 0.693 was attained using cosine similarity. The study concludes by emphasizing the significance of STR in NLP tasks, highlighting the role of pre-trained language models like BERT and Sentence Transformers in enhancing semantic relatedness assessments. © 2024 Association for Computational Linguistics.