Pre-Owned Vehicles Price Predictor

Overview:
In the rapidly expanding automobile industry, new car prices continue to rise with inflation, making used car purchases an increasingly appealing option for budget-conscious consumers. However, the used car market often lacks reliable pricing, with sellers inconsistently valuing vehicles, leaving buyers uncertain if they’re getting a fair deal within their budget.

Problem:
The used car market is plagued by inconsistent pricing, making it difficult for both sellers and buyers to assess the fair value of a car. Sellers may inaccurately define the car’s value, while buyers struggle to determine how much value they’re getting within their budget. Bringing all price data under a unified platform can streamline the car buying process, helping buyers make more informed decisions.

Solution:
This project aimed to create a machine-learning model capable of accurately predicting the price of a used car based on key attributes provided by the customer. Given inputs like car brand, manufacturing year, and two additional features (e.g., mileage, body type, engine type, or fuel type), the model can predict the car’s price with up to 80% accuracy. This tool provides buyers with an efficient way to gauge the value of used cars, enhancing their decision-making in the purchasing process.