Dynamic Pricing Strategies of Product for Minimizing Booking Cancellation: Using Machine Learning Algorithm
Puja Kumari, Abhishek Kumar, Ravi Kumar Burman, Biresh Kumar, Shoaib Alam, Kamaldeep Kamaldeep
Abstract
As already stated in the evaluation of challenges faced within the retail business and especially within winter wear brand, booking cancellations present certain challenges in the competitive environment proffered within the retail business. The goal of this study is to propose the dynamic pricing model with machine learning algorithms to minimize the rate of cancellation of bookings. This model makes the modification of prices based on concerns such as historical booking pattern, customers' preferences and demands, seasonal trends, and competitor's prices. Decision Trees and Random Forest Regression machine learning models are used in an attempt to estimate the probability of cancellation occurrences and consequently the right prices are set to improve on bookings cancellation rate and revenue. Thus, the operational efficiency of the model is examined in terms of numerous trials and practical implementations and discussed certain impacts that the proposed model might have on financial performance of service providers. The revelations would therefore help force contend with dynamic price changes particularly through the use of predictive models to compel productivity enhancements and the resultant improvement in customer satisfaction within the context of a highly competitive retail industry.