.png){kind=icon}
.png){kind=icon}
Return
Combating the bullwhip effect in rival online food delivery platforms using deep learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cie.2026.112021.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A two-phase LSTM model forecasts both intraday and daily demand in online food delivery platforms. • The proposed model significantly reduces the bullwhip effect for Zomato and Swiggy. • Discrete event simulation using SimPy validates model performance over two years of synthetic data. • LSTM forecasts are integrated with a dynamic newsvendor model for managing perishable inventory. • The framework offers actionable insights to minimize waste, prevent stock outs, and improve service efficiency.
Keywords:
LSTM
bullwhip effect
online food delivery
demand forecasting
perishable inventory
Journal
C
IF:
6.5
Papers:
449
Citations:
0