Answers are grounded in this paper and cite their sources.
Evaluates weekend sales forecasting in online shopping, suggesting valuable operational insights.
This study evaluates Multiple Linear Regression (MLR) for prediction of daily online shopping sales with emphasis on weekend demand variation. The analysis uses 1,200 daily observations and four explanatory variables: unique session count, discount percentage, weekend indicator, and campaign flag. Parameters are estimated by ordinary least squares on an 80/20 train-test split, and performance is reported using MSE, RMSE, MAE, and R². The fitted model achieves R² = 0.871, RMSE = ₹9,218, and MAE = ₹6,402 on the hold-out set. Estimated coefficients indicate that session volume and discount percentage are the strongest positive predictors of revenue, while the weekend indicator captures a distinct temporal effect. Residual diagnostics show no strong systematic bias. The contribution of the paper is a compact and interpretable weekend-sales forecasting formulation that links coefficient estimates to operational actions in pricing, campaign timing, and inventory planning. This research paper is prepared for academic and educational purposes as part of MCA Business Analytics research work at CBIT Hyderabad.
No takes yet. Share an insight, caveat, or question.
Tata et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: