In this project, I participated in the Regression of Used Car Prices competition on Kaggle, where the goal was to predict the price of used cars based on various attributes. Leveraging a robust data science pipeline, I conducted exploratory data analysis (EDA) using libraries like numpy, pandas, matplotlib, seaborn, and dython. I applied data preprocessing techniques, including KNNImputer for handling missing values and performed feature engineering to optimize model performance. For model building, I used LGBMRegressor and XGBRegressor, achieving an RMSE of 72738.3121 with LGBMRegressor and 72704.0094 with XGBRegressor. The final predictions were saved in a submission.csv file. The complete code and analysis are available in my Kaggle notebook: https://www.kaggle.com/code/keshabkkumar/car-price-prediction