Personalized Car Recommendations Using Knowledge-Based Methods

The process of selecting a new car can be a complex and challenging task due to the wide range of cars available in the market. To address this issue, this paper proposes a car recommendation system that employs a knowledge-based recommender approach. The system utilizes a variety of car features, including brand, color, year, gear type, number of seats, and price, to provide personalized recommendations for the user. Several models were implemented, such as item-item and user-user models. However, the knowledge-based model outperformed the other models, resolving the cold start problem and producing more accurate recommendations. Overall, the proposed system provides an effective and personalized solution to the car selection process, making it easier for users to find the cars that best match their preferences and needs. The system contributes to the field of recommender systems and could be applied to other domains where personalized recommendations are required.