Integration of Artificial Intelligence in E-Procurement of the Hospitality Industry: A Case Study in the UAE

Thumbnail Image
Journal Title
Journal ISSN
Volume Title
The British University in Dubai (BUiD)
The hospitality industry is growing at an increasingly fast pace across the world which results in accumulating a large amount of data, including employee details, property details, purchase details, vendor details, and so on. The industry is yet to fully benefit from these big data by applying Machine Learning (ML) and Artificial Intelligence (AI). The data has not been investigated to the extent that such analysis can support decision-making or revenue/budget forecasting. The data analytics maturity model is used as the conceptual model for evaluating both data analytics and data governance in this research. In this paper, the author has explored the data and produced some useful visual reports, which are beneficial for top management, as the results provide additional information about the inventoried data by applying ML. Demand forecasting is done using deep learning techniques. Long short-term memory (LSTM) is used to find the demand forecasting of spend and quantity using time lags. The research proposes an extended framework for integrating AI within the e-procurement of the hospitality industry. The AI integrated technologies will enable stakeholders of the industry to be interoperable with all the providers and sub-providers to obtain information easily and efficiently to identify the best solution for their requirements. The proposed framework of integrating AI in the conceptual framework could be used by medium to large enterprises for interoperability, interconnectivity and to take optimum decisions. This paper has uses six ML methods to check the accuracy scoring of the predicted duration of purchase. The duration is predicted using feature variables, including recent purchases, frequency of purchases, spend per purchase, days between the last three purchases, and mean and standard deviation of the difference between purchase days. Logistic Regression, XGBoost, and Naïve Bayes models have proven to be useful for this kind of study where three different scenarios are drawn. Other major results of the research include an answer to what to buy when to buy and how much to buy using demand forecasting for the e-procurement in the hospitality industry. The novel LSTM time series algorithm proved to work best for demand forecasting. Various descriptive, diagnostic, predictive, and prescriptive analysis is done on the e-procurement data. The deep learning model developed can perform thousands of routine and, repetitive tasks within a fairly short period compared to what it would take for a human being without any compromise on the quality of work. Finally, an interview with a subject matter expert is done to evaluate the result and confirm the importance of the study. A survey is also conducted with people involved in the procurement process as part of triangulation. The survey revealed 92% of participants agreed that having an integrated e-procurement framework is very important for the hospitality industry. The integration of AI and ML in e-procurement will revolutionise the hospitality industry.
Artificial intelligence., data analytics maturity model, big data, hospitality, predictive analytics, systematic literature review, e-procurement, machine learning, conceptual framework, demand forecasting