Integrating AI-Driven Sales Analytics and Receivables Recovery Optimization in Enterprise e-Commerce Logistics: A Mixed-Methods Evaluation
DOI:
https://doi.org/10.63125/xkw7s915Keywords:
Artificial Intelligence, Sales Analytics, Receivables Recovery Optimization, Enterprise E-Commerce Logistics, Financial PerformanceAbstract
Enterprise e-commerce organizations generate large volumes of sales, customer, logistics, payment, and receivables data, yet fragmented analytical systems can weaken demand planning, financial risk identification, cash recovery, and coordination between revenue generation and logistics performance. This study aimed to evaluate how the integration of AI-driven sales analytics and receivables recovery optimization is associated with Enterprise E-Commerce Logistics and Financial Performance across enterprise cases. A quantitative, cross-sectional, case-based design was employed, using purposive sampling of professionals working in e-commerce management, sales analytics, business intelligence, data and AI, logistics and supply chain, finance, receivables, credit control, ERP, and CRM. Data were collected through a 25-item questionnaire measuring five constructs on a five-point Likert scale: AI-Driven Sales Forecasting and Predictive Analytics, AI-Enabled Customer and Sales Intelligence, AI-Based Receivables Risk Prediction, Intelligent Receivables Recovery Optimization, and Enterprise E-Commerce Logistics and Financial Performance. Of 320 distributed questionnaires, 299 were returned and 288 were valid, producing a 90.0% usable response rate. Analysis involved descriptive statistics, Cronbach’s alpha reliability testing, Pearson correlation, multiple regression, ANOVA, multicollinearity diagnostics, and Durbin-Watson assessment. The dependent construct recorded M = 4.18, SD = 0.53, while Intelligent Receivables Recovery Optimization achieved the highest predictor mean, M = 4.15, SD = 0.55. All predictors were positively correlated with performance, with Intelligent Receivables Recovery Optimization strongest at r = .74, p < .001. The regression model explained 68.8% of variance, R² = .688, Adjusted R² = .684, F(4, 283) = 156.00, p < .001. Intelligent Receivables Recovery Optimization was the strongest predictor, β = .32, followed by sales forecasting, β = .27, customer and sales intelligence, β = .23, and receivables risk prediction, β = .19, all p < .001. The findings indicate that enterprises can strengthen logistics coordination, financial performance, working-capital efficiency, and cash recovery by integrating predictive sales intelligence with receivables optimization.


