AI-Enhanced Financial Information Systems for Real-Time Fraud Detection and Cash Flow Optimization in U.S. Logistics and Retail Sectors

Abstract

This study examined the role of AI-enhanced financial information systems in improving real-time fraud detection and cash flow optimization in U.S. logistics and retail sectors. The central problem addressed was that many traditional financial information systems remain limited to delayed transaction recording and reporting, making them less effective in detecting suspicious transactions, invoice duplication, refund abuse, payment manipulation, and liquidity risks in fast-moving enterprise environments. The purpose of the study was to quantitatively assess how AI-enabled analytics, automation, anomaly detection, real-time monitoring, and financial data integration influence fraud detection capability, cash flow visibility, operational risk reduction, financial control effectiveness, and decision-making efficiency. The study adopted a quantitative, cross-sectional, case-based design using structured five-point Likert-scale survey data from 250 valid respondents drawn from cloud-enabled enterprise financial system cases in logistics and retail organizations, including finance, accounting, IT, risk, analytics, and operations professionals. Key variables included AI-enhanced financial information systems as the independent variable, real-time fraud detection and cash flow optimization as major dependent variables, and fraud alert responsiveness, Cash Flow Visibility Index, financial control effectiveness, operational risk reduction, and decision-making efficiency as supporting constructs. The analysis plan involved descriptive statistics, reliability testing, validity assessment, Pearson correlation, regression analysis, sector-based comparison, and mediation-style regression. Findings showed strong quantitative support for the model: AI-enhanced financial systems recorded a high mean score of 4.18, real-time fraud detection 4.12, Cash Flow Visibility Index 4.15, and cash flow optimization 4.09. Reliability was strong, with an overall Cronbach’s alpha of 0.91. Regression results showed that AI-enhanced systems significantly predicted real-time fraud detection, β = 0.62, R² = 0.46, p < 0.001, while AI analytics predicted cash flow optimization, β = 0.58, R² = 0.41, p < 0.001. Real-time fraud detection also predicted cash flow optimization, β = 0.49, p < 0.001, and partially mediated the AI system and cash flow relationship. The study implies that AI-enhanced financial systems are strategic financial-control tools for improving fraud prevention, liquidity visibility, risk reduction, and managerial decision-making in transaction-intensive enterprise sectors.