Abstract: The main goal of this project is to predict used car prices, compare prices, and estimate the lifespan of a certain car based on a variety of facts about that vehicle. A new car is reported to lose 10% of its value the moment it is driven out of the dealership. In this circumstance, the number of kilometers the car has been driven is the most important factor in determining its price. As a second consideration, it's important to remember that different car manufacturers price their vehicles differently, which results in price discrepancies between models. In other words, the primary goal of this project is to ensure that the money spent on the car is a good investment for the company itself. We employed supervised machine learning techniques to make predictions about used automobile prices. Kaggle's website is the primary source of data for the predictions. A variety of methods have been employed to predict the outcomes, including multiple linear regression, decision trees, and k-nearest neighbors. They then rank and compare each other's forecasts. Data Which we've gathered in order to determine the greatest performers among them. From this, it's clear that although though this seems like a simple problem, it turned out to be really challenging to solve accurately. All four of these techniques were effective and comparable. We plan to apply more complex algorithms in the foreseeable future to improve the accuracy of our forecasts.

| DOI: 10.17148/IARJSET.2022.9457