Bayesian-optimized ensemble deep learning models for demand forecasting in the volatile situations: A case study of grocery demand during Covid-19 outbreaks

Abstract

Purpose: Lockdown and movement restrictions that imposed by governments have significantly changed customers behavior, making the planning and decision-making processes more challenging. Providing accurate estimation of the demand, enable managers to take more successful decisions and allow optimizing inventory and resources; this is the main purpose of this study.

Design/methodology/approach: An ensemble model that based on combining Bayesian-optimized Long Short-Term Memory (BO-LSTM) and Gated Recurrent Unit (BO-GRU). Experiments were carried out on actual dataset obtained from company specialized in food industries during the volatile situation of Covid-19.

Findings: The proposed model significantly outperformed all hand-tuned ones and reduced the mean Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) by 2.80% and 4.74% compared to BO-LSTM and 3.14% and 3.60% compared to BO-GRU respectively. Furthermore, using BO algorithm for hyperparameters tuning improved the forecasting accuracy.

Originality/value: The suggested model was statistically compared to its members in addition to other machine learning models using the t-test. Findings demonstrated the superiority of the proposed method over all benchmark models.