System Requirements Document (SRD)

Project Name: heroic-car

1. Introduction

The heroic-car project aims to develop a Car Price Prediction App that leverages machine learning to provide accurate price predictions based on user-provided car details. This app will be designed to cater to a wide range of users, including individual car buyers, sellers, dealers, and insurance companies. The project will support dataset input/output in Excel format, making it user-friendly for data exploration and preprocessing.

This document outlines the system requirements for the heroic-car project, ensuring that all functional and non-functional aspects are clearly defined to guide the development process.

2. System Overview

The heroic-car system will consist of a web-based application integrated with a machine learning model for car price prediction. Users will input car details (e.g., brand, model, mileage, year, etc.) through an intuitive interface, and the system will return an estimated price based on the trained ML model.

Key features of the system include:

• Support for Excel format dataset input/output for ease of data handling.
• A user-friendly interface for entering car details and viewing predictions.
• Backend integration with a machine learning model for real-time predictions.
• Secure storage and processing of user data.
• Selective re-run capability for users to manually trigger SRD regeneration.

The system will be designed with scalability and performance in mind, ensuring it can handle a growing user base and large datasets.

3. Functional Requirements

• As a User, I should be able to upload a dataset in Excel format for analysis and model training.
• As a User, I should be able to download processed datasets or results in Excel format.
• As a User, I should be able to input car details (e.g., brand, model, mileage, year, etc.) through a web interface.
• As a User, I should receive an accurate price prediction for the car based on the input details.
• As a User, I should be able to manually trigger a selective re-run to regenerate specific SRD sections.
• As an Admin, I should be able to manage and update the machine learning model.
• As an Admin, I should be able to monitor system performance and user activity.

4. User Personas

4.1 Individual Users

• Description: Car buyers or sellers looking for price estimates.
• Goals: Obtain accurate price predictions for cars based on specific details.
• Technical Proficiency: Basic computer and internet skills.

4.2 Dealers

• Description: Car dealers who want to analyze market trends and set competitive prices.
• Goals: Upload datasets for analysis and download processed results.
• Technical Proficiency: Moderate understanding of data handling.

4.3 Admins

• Description: System administrators responsible for managing the app and ML model.
• Goals: Ensure system reliability, update ML models, and monitor user activity.
• Technical Proficiency: Advanced knowledge of machine learning and system administration.

5. Visuals Colors and Theme

To reflect the modern and innovative nature of the heroic-car project, the following unique color palette is proposed:

• Background: #F4F9FF (soft sky blue)
• Surface: #FFFFFF (pure white)
• Text: #1F2937 (charcoal gray)
• Accent: #FF6F61 (vivid coral)
• Muted Tones: #D1D5DB (light slate gray)

This palette ensures a clean, professional, and visually appealing interface that aligns with the project's purpose.

6. Signature Design Concept

The heroic-car homepage will feature an interactive car showroom experience.

Concept Details:

• Visuals: The homepage will display a 3D rotating car model in the center of the screen. Users can interact with the car by clicking or dragging to rotate it, change its color, or view different angles.
• Background: A dynamic cityscape that changes based on the time of day (e.g., sunrise, daytime, sunset, night).
• Animations: Smooth transitions between sections, with car-related elements (e.g., tires, speedometers) animating as users scroll.
• Interaction: Hovering over different car parts (e.g., wheels, engine) will display tooltips with fun facts or tips about car maintenance.
• Call-to-Action: A prominent "Get Your Car's Price" button that leads users to the input form.

This design will create a memorable first impression and engage users from the moment they land on the site.

7. Non-Functional Requirements

• The system must support Excel format for dataset input/output.
• The system should provide price predictions within 2 seconds of input submission.
• The system must ensure data security and comply with relevant data protection regulations in India.
• The system should be scalable to handle up to 10,000 concurrent users.
• The system should be accessible on both desktop and mobile devices.
• The system should allow users to manually trigger selective re-runs for regenerating specific SRD sections.

8. Tech Stack

Frontend

• React for Web

Backend

• Python
• FastAPI

Database

• MySQL (with Alembic for migrations)

AI Models

• GPT 5.4 for user-friendly responses
• Google Nano Banana for image generation

AI Tools

• Litellm for LLM Routing
• Langchain

Local Orchestration

• Docker
• docker-compose

Server-Side Orchestration

• Kubernetes

9. Assumptions and Constraints

• The dataset provided by users will be in Excel format and must include relevant features for car price prediction.
• Users will have basic knowledge of car details required for input (e.g., brand, model, mileage).
• The system will primarily target users in India, and price predictions will be tailored to the Indian market.
• The machine learning model will be retrained periodically to ensure accuracy.
• Selective re-run capability will be limited to specific SRD sections as defined by the system.

10. Glossary

• Excel Format: A spreadsheet file format (.xls or .xlsx) commonly used for data storage and analysis.
• ML (Machine Learning): A subset of artificial intelligence that uses algorithms to learn from data and make predictions.
• FastAPI: A modern web framework for building APIs with Python.
• Docker: A platform for developing, shipping, and running applications in containers.
• Kubernetes: An open-source system for automating deployment, scaling, and management of containerized applications.
• Selective Re-Run: A feature allowing users to manually regenerate specific sections of the SRD without affecting the entire document.