Second-hand Car Price Prediction Using Machine Learning

Abstract

A new car's price is established by the
manufacturer, with the government paying some additional
costs in the form of taxes. Customers who buy a new car may
feel assured that their money will be wisely spent. However,
due to rising new car prices and purchasers' inability to afford
them, global used car sales are expanding. As a result, a Used
Car Price Prediction system that can reliably appraise a car's
worth based on a variety of characteristics is in high demand.
We look at how supervised machine learning techniques may
be used to predict the price of used cars in this study. The
prediction is based on historical data gleaned from daily
newspapers. Several methods were used to construct the
predictions, including multiple linear regression analysis,
Random Forest Regression, Random Forest Regression, and
Randomized Search cv. We will use several characteristics
such as Present Price, Selling Price, kilometers Driven, Fuel
Type, Year, and others to anticipate the price of used cars in
this Project. Kaggle was utilized to obtain the data for this
Project. After then, the forecasts are analyzed and compared
to see which ones provide the best outcomes. A seemingly easy
problem turned out to be rather difficult to solve precisely. All
four techniques had similar outcomes. So the model helps to
predict cars actual price rather than predicting car's price
range. A user interface has also been created that collects
input from any user and displays the price of a car based on
the information provided by the user.
**Knowing how to evaluate the market worth of used cars
may be beneficial to both buyers and sellers**
There are lots of individuals who are interested in the used
car market at some points in their life because they wanted to
sell their car or buy a used car. In this process, it’s a big corner
to pay too much or sell less then its market value. In the future,
we intend to use more complicated algorithms to generate
predictions