Learn how to predict the price of used cars in the US using machine learning. Analyze a dataset of 3 million cars, clean the data, and train & evaluate different models. Includes code & markdown.
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
- Download the dataset
- Data Cleaning
- Exploratory Analysis and Visualization
- Prepare the dataset for ML training
- Train hardcoded & baseline models
- Make predictions
- Peform feature engineering
- Train & evaluate different models
- Tune hyperparameters for the best models
- Summary and References
Download The Dataset
Steps:
- Install required libraries
- Download data from Kaggle
- View dataset files
!pip install numpy pandas jovian opendatasets scikit-learn xgboost --quietimport jovian