About the website
A low-latency Bitcoin trading bot, built by students, designed for students.
This project is a student-built Bitcoin trading bot created for a competition. Instead of hiding everything behind a black box, we focused on clear structure: live data, rule-based strategy, transparent UI, and a full trade history.
How the bot works
Our system uses a Genetic Algorithm (GA), an optimization method inspired by evolution. Instead of following fixed rules, the bot learns from experience, adapts to conditions, and evolves toward smarter decisions.
- 1Population of strategies
The bot generates multiple strategy variants. Each individual has different parameters: entry timing, risk, exit behavior, and leverage profiles.
- 2Fitness evaluation
Each strategy is tested on market data. We evaluate profit, drawdown, stability, and consistency. Better-performing strategies score higher.
- 3Mutation + crossover
The top strategies “breed” new ones. Their parameters mix together, and small mutations introduce new behaviors, helping the bot explore new profitable patterns.
- 4Evolution over time
Over many generations, the bot learns what works. The engine evolves, adapts, and improves automatically with each iteration.
Full Processing Pipeline
Live market ticks →WebSocket feed streams every trade and micro-movement from Binance.
Data preprocessing →Converts ticks into candles, depth snapshots, and volatility readings.
Strategy engine →The Genetic Algorithm evaluates signals, thresholds, momentum and trend slopes.
Execution layer →Simulated entries/exits are triggered with controlled risk rules.
Logging →Every action is stored in Bot History for full transparency and review.
Engine Specifications
- Market Data: Binance BTC/USDT WebSocket feed
- Strategy Model: Genetic Algorithm (GA), evolving every generation
- Population Size: 50 individuals per generation
- Evaluation Window: Short & long moving averages, dynamic volatility
- Execution Mode: Simulated spot positions (no real funds)
- Platform Stack: Next.js, Zustand, TradingView, WebSockets
Why we built it
Our goal isn’t to promise perfect profits. Our goal is to show that we understand how to design a real trading system: data, logic, risk management, and UI working together in a transparent way.
Every trade is fully visible and logged, enabling proper analysis, learning, and honest demonstration of strategy behavior.
About our team
We’re three young engineers building proprietary trading software from scratch. Our skill sets cover modern automated trading: live feeds, strategy logic, quantitative design, UX, and software architecture.
This isn’t a class project — it’s a proving ground. Talent, consistency, and curiosity over everything else. No shortcuts. Just real engineering.
Mission Statement
Our mission is to build transparent, educational, and high-performance trading technology that helps students understand real market structure through live data and intelligent automation.
Our Values
- • Transparency over hype
- • Learning through real data
- • Engineering before shortcuts
- • Curiosity and experimentation
Vision
Our vision is to transform this simulator into a fully autonomous research platform where students can test ideas, benchmark algorithms, and explore AI-driven trading safely.