Effect of AI and Machine Learning–Driven Demand Forecasting on Retail Performance of Jumia Nigeria

The rapid evolution of e-commerce in emerging markets has made AI and Machine Learning–driven demand forecasting a critical driver of retail performance. This study examined the effect of AI and ML–driven demand forecasting through the dimensions of Forecasting Accuracy, Predictive Inventory Planning, and Automation in Order Prediction on the Retail Performance of Jumia Nigeria, measured via sales efficiency, inventory turnover efficiency, and operational responsiveness. Employing a quantitative cross-sectional design, primary data were collected from all 228 eligible employees involved in demand forecasting, inventory management, supply chain planning, merchandising, data analytics, and marketplace operations at Jumia Nigeria. A total of 184 fully completed questionnaires were returned, yielding a high response rate of 80.7%. Data were analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM) with SmartPLS 3 software. Results revealed that Forecasting Accuracy (β = 0.394, t = 5.834, p = 0.000) and Predictive Inventory Planning (β = 0.334, t = 3.829, p = 0.000) exert strong, statistically significant positive effects on Retail Performance, leading to the rejection of H₀₁ and H₀₂. In contrast, Automation in Order Prediction (β = 0.131, t = 1.569, p = 0.117) showed a positive but non-significant relationship, resulting in the acceptance of H₀₃. The model explained 65.6% of the variance in Retail Performance (R² = 0.656, Adjusted R² = 0.654), with excellent reliability, convergent and discriminant validity, and good model fit (SRMR = 0.064). These findings indicate that, at Jumia Nigeria, superior retail performance is primarily driven by high forecasting accuracy and its translation into predictive inventory decisions, while automation currently plays a supportive rather than direct role. The study recommends that Jumia Nigeria prioritise continuous enhancement of AI/ML forecasting models and real-time data integration, progressively expand automation capabilities, and advocate for policy support to accelerate AI adoption across Nigeria’s retail sector.