Daily Archives: October 21, 2026

Authors: Dr. A. Joy

Abstract: The recent explosion in the use of digital payment systems has created large amounts of data relating to customer payments. In this paper, a predictive analytical framework is proposed which will be useful for modelling spending behavior in digital payment systems. The framework uses temporal encoding of data which takes into account the type of data along with the other characteristics of the data. It also utilizes dynamic graph learning of structures and spatial-temporal convolutions in order to take into account the relationships between the transactions as well as their time-based aspects. The key difference between the proposed framework and traditional approaches lies in the fact that it considers the relationships between different spending categories and allows these relationships to change over time for each individual consumer. Experimental evaluations performed on a digital payment system dataset have shown that the proposed framework performs better in terms of accuracy than traditional baselines like ARIMA, Prophet, and LSTM.

DOI:

Published by: vikaspatanker

Authors: Mrs.N.Zabina

Abstract: With growing adoption of e-commerce platforms, the problem of identification of fraudulent financial transactions in a real-time manner has increased manifold. Current approaches of rules-based approaches and stand-alone machine learning models have faced difficulty adapting and dealing with novel types of fraud cases when there is heavy class imbalance and only few examples of frauds out of the total volumes. In this research, we propose the novel hybrid system of fraud detection for e-commerce using techniques of isolation forest, representation learning via autoencoder, and supervised learning using xgboost for classification. Unsupervised learning using anomaly detection is used to identify statistical anomalies as well as reconstruction-based outliers and supervised gradient boosting approach is used to improve the decision boundaries on labeled data. Evaluation experiments performed on large-scale anonymous transaction dataset show better discriminative performance of our hybrid approach as compared to the current benchmark models with respect to both the F1-score and AUC score. An explainable approach using SHAP values is provided as part of our framework, complying to regulations on explainability.

DOI:

Published by: vikaspatanker