Dynamic Pricing for Revenue Management in Health and Hospitality Industry with Federated Learning

Revenue management with dynamic pricing (DP) has emerged as a greater outstanding subject of matter to study regarding online food delivery in Health and Hospitality Industry. As well as with the use of online travel agencies (OTA), also due to sizeable development within the fields of statistics, economics, and facts of technology in the recent studies federated learning (FL) with long short-term memory (F-LSTM), the pricing which could be done efficiently. DP is a powerful method for pricing hotel rooms and food products, by adjusting the rates based on demand and merchandise primarily based totally on the call for fluctuations over time to manage the revenue, hotels are capable of maximizing their profits using revenue management software (RMS). By utilizing those techniques, hotel groups can highly recognize what they have achieved in the past, make essential modifications to their pricing techniques to keep up with marketplace needs, and think about statistics that can be volatile. The motive of FL is to utilize multiple datasets to make decisions concerning DP. Luxury hotel data need to be trained to predict the pricing of rooms and food products, the primary objective is to handle the hotel data while preserving privacy; FL supports the multiple data to be trained with privacy; in addition, LSTM for DP pricing of the hotel room-based on demand under the best circumstance, seasonal demand keeps changing and hotel profit gets affected if the rooms are not occupied and the foods are not sold. This chapter proposes a novel LSTM algorithm, with FL to understand the buying behavior of hotel guests for food and rooms and to price rooms and rooms according while keeping the data safe.