Novel intelligent supervised neuro-structures for nonlinear financial crime differential systems

Abstract

Artificial intelligence (AI)-based applications contribute to monitoring financial transactions and detect fraudulent activity in real-time by analyzing transaction patterns, consumer behavior, and other statistics, making them essential for quickly addressing potential threats in the fight against financial crime dynamics. Leveraging financial crime systems with intelligent supervised neuro-structures exploiting nonlinear autoregressive exogenous networks integrating damped least square (NARX-DLS) optimization methods to achieve an appropriate degree of accuracy and adaptability for the estimation of complex nonlinear financial crime differential systems (NFCDSs). The representative NFCDS for financial crime indicators is expressed as susceptible individuals, financial criminals, individuals under prosecution, imprisoned individuals, and honest individuals. The Adams numerical solver accomplishes the acquisition of synthetic data for the layer structure NARX-DLS algorithm execution to solve NFCDSs for various financial crime parameters, such as recruitment rate, influence rate, conversion rate to honest people, financial criminal prosecution rate per capita, discharge and acquittal rate from prosecutions, percentage of discharge rate from prosecution, transition rate to prison, and freedom rate. A sturdy overlap between the solutions of NARX-DLSs and the reference numerical results of NFCDSs implies that the error value is close to a desirable value of zero. The effectiveness of the NARX-DLSs is evidenced by including a variety of assessment metrics that carefully examine the model’s correctness and efficacy, including mean square error-based convergence arches, adaptive regulating parameters, error distribution, and input-error/cross-correlation analyses.