The LSTM technique for demand forecasting of e-procurement in the hospitality industry in the UAE

Elezabeth Mathew, Sherief Abdulla


The hospitality industry is growing at a faster pace across the world which has resulted in the accumulation of a huge amount of data in terms of employee details, property details, purchase details, vendor details, and so on. The industry is yet to fully benefit from these big data by applying ML and AI. The data has not been fully investigated for decision-making or revenue/budget forecasting. In this research data is collected from a chain hotel for advanced predictive analytics. Descriptive and diagnostic analytics is done to an extent across the hotel industry, whereas predictive and prescriptive analysis is done rarely. Demand forecasting for spend and quantity is done using the LSTM technique in e-procurement within the hospitality industry in the UAE. Five years of historical data from a chain hotel in the UAE is used for deep learning in this study. The results confirm the ability of LSTM model to predict e-procurement spend and order forecast for six months. LSTM time series analysis is considered the most suitable technique for demand forecasting to optimize e-procurement.


Deep learning, Demand forecasting, E-procurement, Hospitality, Long- and short-term memory, Machine learning

Full Text:




  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

IAES International Journal of Artificial Intelligence (IJ-AI)
ISSN/e-ISSN 2089-4872/2252-8938 
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

View IJAI Stats