Design and development of an intelligent system based on artificial intelligence and machine learning using customs digital indicators

This paper aims to evaluate the role of AI and ML-driven innovative technologies in enhancing customs operations in Jordan. This research employed a quantitative approach to develop an overall conceptual model that encompasses both the technical and behavioral aspects of intelligent system adoption. The target population consisted of customs officers, border security personnel, and IT personnel responsible for customs clearance and trade facilitation in Jordan. The structured questionnaires were administered to the respondents to measure their perceptions of system effectiveness, satisfaction, performance outcomes, and evasion behavior and yielded a total of 358 valid responses. The research was conducted with proper statistical analysis, and the statistical techniques employed included primary data collected via SPSS Version 29 and advanced modeling using Structural Equation Modeling-Partial Least Squares (SEM-PLS) through the use of SmartPLS 4.0. The results indicated that the measurement model proved to be both valid and reliable, with Cronbach's alpha values exceeding 0.82 and AVE values above 0.50, indicating good internal consistency and convergent validity. Moreover, the structural model achieved good explanatory power, with R² values of 59% for Customs Evasion, 43% for User Satisfaction, and 100% for Digital Performance Indicators. These findings underscore the significance of user satisfaction as a key outcome of system effectiveness and a valuable tool for enhancing performance and deterrence. More specifically, the results shown how Intelligent System Effectiveness presents a positive and significant impact on User Satisfaction (β = 0.656, p < 0.001), which in turn has a high positive effect on both Digital Performance Indicators (β = 1.000, p < 0.001) and Customs Evasion reduction (β = 0.770, p < 0.001). The mediation analysis also confirmed that User Satisfaction fully mediates the relationship between system effectiveness and performance outcome, as well as between system effectiveness and evasion reduction. This research contributes to theory and practice by demystifying the design and implementation of AI-driven customs systems. It illustrates the importance of valuing both technical system quality and user-centric values in achieving and maintaining optimal performance in the digital space, as well as conformance with the law.