Faculty Publications

Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736

Publications by NITK Faculty

Browse

Subject: search.filters.subject.Financial technology

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Multi-level Attention driven GAT for recommending top profitable stocks and sectors
    (Institute of Electrical and Electronics Engineers Inc., 2025) Phadatare, A.; Patel, M.M.; Mohan, B.R.; Chaithra
    Financial technology has drawn significant attention from investors and companies. Recently there is growing demand in use of graph networks for time series data. While traditional stock analysis primarily focuses on predicting stock prices, there is comparatively less emphasis on recommending profitable stocks. Neglecting relationships between stocks and sectors can miss crucial shared information. In this work, we aim to recommend the top profitable stocks and sectors, utilizing time series data of stock prices and sector information. We introduce a novel deep learning-based model, Multilevel-Attention based Graph Attention Network designed to incorporate relationship between both stocks and sectors and rank them. First, we created a dataset for Indian stock market of NIFTY50 companies. Second, we used LSTM to create embedding and constructed fully connected graphs for stocks and sectors, and then using graph attention networks to learn latent interactions among them. Lastly, we used Multi-level and Hierarchical attention networks to rank the stocks and sectors. Comparing our multi-level attention approach to an approach with the absence of multi-level attention, the mean F1 score increased from 0.256 to 0.309, showing an improvement of 20.84%. Similarly, mean accuracy score increased from 0.251 to 0.388, showing an improvement of 54.40%. The implication of our research is varied as it can be applied in numerous scenarios like forecasting, helping in managing portfolios and assessing risks by analyzing trends and patterns of stocks. © 2025 IEEE.
  • No Thumbnail Available
    Item
    Louvain community-based label assignment for reject inference in peer-to-peer lending
    (Springer Science and Business Media Deutschland GmbH, 2025) Hegde, A.; Bhowmik, B.; Bennehalli, S.; Vakkund, S.
    The digital transformation in the Financial Technology (FinTech) sector has significantly altered traditional banking and lending practices, giving rise to innovative models like peer-to-peer (P2P) lending. P2P lending platforms directly connect lenders and borrowers online, bypassing conventional financial intermediaries and democratizing access to finance. However, this innovation introduces new complexities in the risk assessment process, necessitating advanced analytical methods. This research presents Accept-Reject-Net framework, a three-step modeling approach designed to capture and evaluate the complex relationships of loans within the accept and reject dataset, a crucial aspect of P2P lending. Initially, the datasets are separated using two outlier detection methods that efficiently manage extensive datasets by distinguishing inliers (data points adhering to a specific pattern) from outliers (data points deviating from the anticipated pattern). We then generate four distinct merged datasets by applying two different ratios of accept and reject data. In the second stage, borrowers are systematically represented as nodes, with their Euclidean distances as edges, allowing us to extract graph features that effectively capture the structural attributes and similarities of the loans. These graph features are used to classify entries in the Reject dataset as either default or non-default. Two distinct approaches are introduced Louvain mode and Louvain threshold to facilitate label assignment within detected communities. The threshold is validated across multiple levels to assess its effectiveness in refining label assignment. In the third phase, these features are inputs for training five machine learning models, further enhanced with additional labeled data. To ensure the reliability and robustness of our findings, confidence intervals and permutation tests are used to assess the performance differences between different partitions. The 7:1 ratio of accept:reject with the threshold method of Louvain community detection for assigning labels to the rejected dataset improves the metrics, making the model much more effective for reject inference. This comprehensive approach addresses the biases inherent in traditional credit scoring models and enhances the predictive accuracy and fairness of loan evaluations. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.