This dataset contains information about ~38000 cars listed on Cardekho.

There are three CSV files in this dataset -

• cars_overview.csv : Overview of the cars, contains basic info about the cars such as transmission type, location and the listing price.
• car_details.csv : This file contains the almost all the cars in the overview file along with many other details, such as the features of the cars, the type of owner, etc.
• car_details_merges.csv : This file is the merged version of the above two files, contains the basic as well as the detailed information of all the cars.
• feature_dictionary.csv : Since the data is quite big, this file explains what information each column in the dataset has.

Points to note about the data:

1. The dataset contains columns which can have duplicate information since the data is scrapped using an API. It is advised to clean the data before using it.
2. There are multiple unique identifiers for each car, but using usedCarSkuId is recommended.
3. The price of the cars is under the column named price which has values such as ₹ 3.50 Lakh. We also have another column indicating the price in a continuous variable type called pu

Disclaimer This data is meant for academic and research purposes and should not be used for commercial purposes.