A predictive analytics approach for forecasting bike rental demand

The demand for rental bikes in urban areas fluctuates, leading to localized surpluses and shortages. To address this challenge, effective bike relocation strategies are essential for ensuring equitable distribution and maximizing customer satisfaction. This study aims to employ advanced machine learning techniques to forecast bike rental demand in urban areas, thereby enhancing the efficiency and accessibility of bike rental services and contributing to sustainable urban mobility. The study comprehensively analyzes various influencing factors using machine learning models, including Ordinary Least Squares regression, MLP Regression, Gradient Boosting Regression, Random Forest Regression, Polynomial Regression, and Decision Tree Regression. The primary objective is to identify the most accurate predictor by comparing key metrics such as R-squared (R2), Mean Squared Error (MSE), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Pearson Correlation Coefficient. Insights gained from this analysis aid in identifying influential variables and ensure the development of resource-efficient and adaptable models, leading to more informed decision-making for rental bike businesses. Additionally, future research directions involve the implementation of artificial intelligence technology to predict overall bike demand based on urban cities' criteria, including the number of national and international tourists. By addressing these objectives, this study seeks to provide valuable insights and tools for rental bike businesses to optimize operations, make strategic decisions, and enhance customer experience in competitive urban markets.