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:
