Published Paper Details:

In today's automotive market, accurately predicting car prices is crucial for various stakeholders, including manufacturers, dealerships, and consumers. Machine learning (ML) algorithms offer a powerful tool for building predictive models that can analyze numerous factors and provide insights into pricing trends. This paper presents a car price prediction model utilizing ML algorithms. The model aims to forecast the prices of used cars based on various features such as make, model, year, mileage, fuel type, and more. By leveraging historical data on car sales and their associated attributes, the model learns patterns and relationships to make accurate price predictions for unseen vehicles. The proposed model employs a Random Forest Regression algorithm, which is well-suited for handling complex datasets with nonlinear relationships. Random Forest Regression combines the predictive power of multiple decision trees, leading to robust and accurate predictions. Additionally, feature engineering techniques are applied to preprocess and transform raw data, enhancing the model's performance. To evaluate the model's effectiveness, extensive experiments are conducted on a real-world dataset comprising information about thousands of used cars. Performance metrics such as mean absolute error (MAE), mean squared error (MSE), and R-squared (R2) are used to assess the model's predictive accuracy and generalization capabilities. The results demonstrate that the proposed car price prediction model achieves high accuracy and outperforms baseline methods. Furthermore, sensitivity analysis is performed to identify the most influential features affecting car prices, providing valuable insights for stakeholders in the automotive industry. Overall, this research contributes to the field of car price prediction by presenting an effective ML-based approach that can assist in making informed decisions related to car pricing, buying, and selling.