Learn practical skills, build real-world projects, and advance your career

Used Cars Price Prediction using ML


  • Dataset Used: US Used Cars Dataset(3 million Cars)

  • We'll train the machine learning model to predict the price of a second hand car in USA given the information like Engine Power, Car Make, Car Condition, Seller Rating, Selling location, Seating Capacity etc.

  • In this project, we analyse the US Used Cars Dataset(3 million Cars), which has information about '3 million' cars listed in the Used Car Market in US.

  • The dataset has 3 million rows and 66 columns

  • To run this notebook, select "Run" > "Run on Colab" and connect your Google Drive account with Jovian. Make sure to use the GPU runtime if you plan on using a GPU.

Steps Followed

  1. Download the dataset
  2. Data Cleaning
  3. Exploratory Analysis and Visualization
  4. Prepare the dataset for ML training
  5. Train hardcoded & baseline models
  6. Make predictions
  7. Peform feature engineering
  8. Train & evaluate different models
  9. Tune hyperparameters for the best models
  10. Summary and References

Download The Dataset


  • Install required libraries
  • Download data from Kaggle
  • View dataset files
!pip install numpy pandas jovian opendatasets scikit-learn xgboost --quiet
import jovian