← Back to all models
Regression

Used Car Prices

Uses the car's age, kilometers driven, and original price to predict what it would sell for today.

Try It Yourself

Enter values below, then hit Predict to see what the model says.

Raw Dataset (original data)
Car_NameYearSelling_Price_USDPresent_Price_USDKms_DrivenFuel_TypeSeller_TypeTransmissionOwner
Cleaned Dataset (the version we feed to the model)
Car_Age_YrsKilometers_DrivenOriginal_PriceSelling_Price
The Code (how we built this model) 
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score

df = pd.read_csv('used_cars_original.csv')

df = df[['Year', 'Kms_Driven', 'Present_Price', 'Selling_Price']]

df = df.dropna()

df = pd.get_dummies(df, drop_first=True)

X = df.drop('Selling_Price', axis=1)
y = df['Selling_Price']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

scaler = MinMaxScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)

model = LinearRegression()
model.fit(X_train, y_train)

y_pred = model.predict(X_test)
print(r2_score(y_test, y_pred))
Under the Hood (the equation the model learned)
Price = $3,264 − $533 × Age − $0.00 × Kms + $0.52 × Original Price

Age is the main killer of value (−$533/year). Kilometers driven barely matters at this scale. And you recover about 52 cents on every dollar of original price.

Try the Equation Yourself

Predicted Result —