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

Elezabeth Mathew, Sherief Abdulla

Abstract


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.

Keywords


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

Full Text:

PDF


DOI: http://doi.org/10.11591/ijai.v9.i4.pp757-765

Refbacks

  • There are currently no refbacks.


View IJAI Stats

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