Skip to content

Latest commit

 

History

History
22 lines (18 loc) · 1.41 KB

File metadata and controls

22 lines (18 loc) · 1.41 KB

Requirements Document: Car Price Prediction AI

1. Project Overview

The goal of this project is to develop a machine learning model that accurately predicts the market value of used cars based on various features such as brand, mileage, fuel type, and transmission.

2. Functional Requirements

  • Data Ingestion: The system must be able to process structured data (CSV or JSON) containing historical car sales records.
  • Preprocessing: The system must handle missing values, encode categorical variables (e.g., One-Hot Encoding for Brand), and scale numerical features.
  • Price Prediction: The core AI model must provide a continuous numerical output (Price) based on user input features.
  • User Interface: A simple interface (Web or CLI) where users can input car details and receive an instant valuation.
  • Accuracy: The model should aim for an R-squared value of 0.85 or higher on the test dataset.

3. Non-Functional Requirements

  • Performance: The model inference time should be less than 200ms per request.
  • Scalability: The architecture should allow for adding more training data as it becomes available.
  • Usability: The input form should validate data types (e.g., mileage cannot be negative).

4. Technical Stack

  • Language: Python 3.x
  • Libraries: Pandas, Scikit-Learn, NumPy
  • Framework: Flask or Streamlit (for the UI/API)
  • Model: Random Forest Regressor or XGBoost