JoWUA

Abstract

Proper sales prediction is essential in retail businesses such as BigMart in order to maximize inventory, pricing policies, and business decisions. This research paper presents a superior forecasting model that integrates Recurrent Neural Networks (RNNs) and Explainable Artificial Intelligence (XAI) methods to predict BigMart sales. The framework learns both the short- and long-run temporal dynamics in the sales data by training an RNN model on past transactional history, product attributes, and store-level features. To make the model more transparent, we combine XAI techniques, i.e., SHAP (Shapley Additive explanations) and LIME (Local Interpretable Model-Agnostic Explanations), and identify the most essential features that drive sales predictions. The following performance measures are used to test the proposed model: Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and R2. Findings indicate that the RNN-XAI model outperforms traditional models, such as ARIMA and XGBoost. In particular, the RNN-XAI model yields the following results: RMSE = 93.14, MAE = 72.45, MAPE = 8.11, and R2 = 0.94, indicating strong predictive power and strong explanatory features. This underscores the fact that variables such as Item MRP, Outlet Type, and Seasonal Indicators have a significant effect on sales. Not only does the XAI integration enhance the model's accuracy, but it also provides insights that non-technical stakeholders can easily interpret and have confidence in the forecast. The given approach demonstrates the potential of combining deep learning and XAI to enhance retail industry decision-making.