The Impact of Employee’s Awareness of Food Safety in Egyptian Hotels: Machine Learning Approach

Abstract

Hotel management food awareness has improved greatly using AI. Several scholars are interested in using the newest machine learning (ML) methods to enhance food quality, nutrition, safety, and accountability. Its operating systems use ML approaches to enhance service quality, profitability, resource optimization, and food waste reduction in the hotel industry. ML might improve demand, price, booking cancellation, financial, and labor efficiency. Hotels’ reputations depend on client happiness and loyalty, making food safety one of the most important challenges in the food industry. Thus, hotels have used customized ML technologies to assess staff food safety knowledge. This research also aims to prove the impact of Egyptian hotel employees’ food safety awareness by distributing questionnaires to kitchen department employees on food safety (i.e., personal hygiene, cross-contamination prevention and sanitation, preparing food). Of the 250 forms distributed, 230 were valid for statistical analysis with a percentage of 92.8%. The main results showed that employee awareness (personal hygiene and food preparation) and food safety in Egyptian hotels are positively correlated, indicating a significant difference between food preparation and personal hygiene training courses (p-value= 0.05). Our suggested model predicts hotel staff awareness using ML approaches utilizing questionnaire data. The improved Support Vector Machine algorithm was evaluated using 10-fold-cross validation and obtained 99% accuracy, 99% recall, and 99% F1-score using our questionnaire data to assess employee food safety knowledge. This research should help build ML-based solutions for Egyptian hotel food production.