hardy-system

Introduction

The hardy-system is an AI-powered application designed to predict football match outcomes. It targets casual football fans, providing them with insights and predictions to enhance their viewing experience.

System Overview

The hardy-system leverages advanced AI models to analyze historical data, team performance, player statistics, and other relevant factors to predict the outcomes of football matches. The system is designed to be user-friendly, catering to casual fans who may not have in-depth knowledge of football analytics.

Functional Requirements

• As a casual fan, I want to receive predictions for upcoming football matches so that I can make informed decisions.

• As a casual fan, I want to view detailed analysis and statistics of past matches to understand prediction accuracy.

• As a casual fan, I want to receive notifications about match predictions and updates.

• As a casual fan, I want to customize the types of notifications I receive based on my preferences.

• As a casual fan, I want to share predictions and insights with friends on social media platforms.

• As a casual fan, I want to access the application on both web and mobile platforms for convenience.

• As a casual fan, I want to see additional features that enhance my experience, such as player performance insights and team news.

• As a casual fan, I want the application to help me find piracy sites for streaming matches.

User Personas

• Casual Fan: A user who enjoys watching football matches and is interested in predictions and insights to enhance their viewing experience. They are not necessarily experts in football analytics but appreciate easy-to-understand information.

Core User Flows

• Casual Fan uses the app to find piracy sites for streaming matches.
• Casual Fan opens the app -> selects upcoming matches -> views predictions and insights -> shares predictions on social media.
• Casual Fan receives a notification -> opens the app -> views detailed match analysis -> customizes notification settings.

Visuals Colors and Theme

• primary: #3B5998 (a deep blue to represent trust and reliability)
• primary_light: #8B9DC3 (a lighter blue for hover states and secondary UI)
• secondary: #FF6F61 (a coral hue for headlines and emphasis)
• accent: #FFD700 (a vibrant gold for CTAs and active states)
• highlight: #FFA500 (an orange for hover states and notifications)
• bg: #F5F5F5 (a light grey for the page background)
• surface: rgba(255, 255, 255, 0.9) (a white card/panel background)
• text: #333333 (a dark grey for primary text)
• text_muted: #777777 (a softer grey for secondary text)
• border: rgba(0, 0, 0, 0.1) (a subtle black border)

Signature Design Concept

The hardy-system will feature an interactive football pitch on the landing page. Users can click on different areas of the pitch to reveal match predictions, player stats, and team insights. The pitch will be animated using framer-motion to provide smooth transitions and interactions. As users hover over different sections, the pitch will highlight relevant data points, creating an engaging and informative experience.

Interaction Model & Motion Direction

The landing page will utilize a "parallax" interaction model, where the football pitch and its elements move at different speeds as users scroll. This layered depth effect will create an immersive experience, drawing users into the world of football analytics. Internal pages will maintain a "static" interaction model to ensure clarity and ease of use for data-heavy content.

Non-Functional Requirements

• The system should provide predictions with an accuracy rate of at least 75%.
• The application must load predictions and insights within 2 seconds.
• The system should handle up to 10,000 concurrent users without performance degradation.
• The application must be accessible on both web and mobile platforms.

Tech Stack

• Frontend: React for Web, React Native for mobile app
• Backend: Python, FastAPI
• Database: MySQL or MariaDB
• AI Models: GPT 5.4 for user-friendly response
• AI Tools: Litellm for LLM Routing
• Local Orchestration: Docker, docker-compose
• Server-side Orchestration: Kubernetes

Assumptions and Constraints

• The application will primarily target casual football fans, so the interface must be intuitive and easy to navigate.
• Predictions are based on historical data and AI models; real-time data integration is not within the current scope.
• The system will not support betting or gambling features.

Glossary

• AI: Artificial Intelligence
• CTA: Call to Action
• UI: User Interface
• LLM: Large Language Model
• RDBMS: Relational Database Management System
• API: Application Programming Interface