The car rental industry, integral to global travel and transportation, has seen substantial evolution over the past decade, spurred by technological advancements and changing consumer expectations. Central to this industry's operational efficiency is the ability to accurately forecast demand, which informs fleet management, pricing strategies, and customer service. Traditional demand forecasting methods have often failed to address the complexity of market dynamics. However, the advent of data analytics and sophisticated techniques in artificial intelligence have introduced more precise predictive capabilities.

This study conducts a systematic review of the literature from the past ten years to assess the application of Intelligent models in demand forecasting within the car rental industry. Using databases like Scopus and IEEE Xplore, a total of 254 studies were initially identified, with 11 meeting the inclusion criteria for in-depth analysis. The review examines various Intelligent techniques, their effectiveness, and the impact of different data types on model performance. The findings highlight common methodologies, key predictive factors, and performance metrics, such as Mean Absolute Error and Root Mean Squared Error. Models like Convolutional Neural Networks, and ensemble methods demonstrated superior accuracy.

Despite these advancements, challenges remain, including data redundancy, computational complexity, and the need for extensive feature engineering. This study provides a comprehensive synthesis of current approaches, identifies gaps like the lack of interpretability of existing models, and suggests future research directions to enhance demand forecasting accuracy and operational efficiency in the car rental sector.

Keywords: Car rental industry, Demand forecasting, Pricing strategies, Machine Learning, Artificial intelligence