Optimization Techniques for Car Price Prediction
This study compares the effectiveness of various machine-learning algorithms and optimization techniques, and it suggests a novel machine- learning strategy paired with optimization algorithms for car price prediction that would be made simpler and more adaptable by applying machine learning techniques to the issue.
Abstract
The optimization is a key concept in machine learning, it can be used to find the best parameters for a machine learning algorithm, or to find the best way to solve a problem. Price determination for a secondhand car is typically a laborious and error-prone process if done manually. However, this method would be made simpler and more adaptable by applying machine learning techniques to the issue. This can be viewed as a prediction task using machine learning, where the model will be trained on previously collected data while also emphasizing the factors that impact price most. This study compares the effectiveness of various machine-learning algorithms and optimization techniques, and it suggests a novel machine-learning strategy paired with optimization algorithms for car price prediction. This kind of regression problem can be solved using a variety of machine-learning methods. These techniques can be used in conjunction with optimization algorithms to raise the model's overall prediction efficiency and accuracy. In this work, we tried seven optimization algorithms for model building and find the effectiveness of those algorithms. Finally using the Genetic algorithm and Random forest we achieved an R2 score of 0.91, a Mean absolute error of 01.49, a Mean squared error of 10.27, and a Root mean squared error of 03.20.