This project aims to predict the selling prices of used cars based on various features such as brand, model year, mileage, and engine specifications. The dataset includes detailed information about numerous vehicles. The primary goal is to develop models that accurately estimate car prices, helping potential buyers and sellers make informed decisions.
Project Objectives
-Perform exploratory data analysis (EDA) to uncover key insights and patterns within the dataset.
-Build and evaluate machine learning models to predict car selling prices.
-Compare the performance of multiple models, starting with Linear Regression and advancing to ensemble methods.
Data Preprocessing:
-Handle missing values and remove duplicate entries
-Feature engineering
-Clean and standardize key attributes
Exploratory Data Analysis (EDA):
Visualize relationships between variables, such as model year and selling price, to identify trends and correlations.
Analyze the impact of various factors, including engine specifications and ownership history, on car pricing.
Model Building and Evaluation::
Initially trained a Linear Regression model, achieving an R-squared: of 62%
Implemented ensemble methods, which significantly improved performance to R-squared: of 98%
