HeyTraders
Personal AI quant research & backtest with natural language
156 followers
Personal AI quant research & backtest with natural language
156 followers
HeyTraders is a Personal AI Quant for crypto markets that translates natural language into verifiable trading strategies. Stop trading based on gut feelings and complex charts. Just talk to our agent to research trends, verify ideas with instant backtesting, and get data-driven confidence.
HeyTraders
Hi Hunters! 👋 I’m Soonbeom, founder of HeyTraders.
The Story: I previously worked as a quantitative researcher at a crypto trading firm. Back then, I could focus on finding alpha because a dedicated engineering team handled the data and infrastructure.
But when I tried to trade my own strategies as an independent quant, I hit a wall. I spent 90% of my time building data pipelines and backtesting engines from scratch, and only 10% on actual trading. I realized: "Retail traders don't lack ideas. They lack the infrastructure."
The Solution: That’s why I built HeyTraders. It’s a Personal AI Quant that integrates research, backtesting, and validation into one conversation.
What you can do right now (MVP):
🔍 Ask Anything: "Why is Bitcoin moving today?" Our agent summarizes the key drivers.
📊 Verify Your Ideas: Just describe your strategy in plain English (e.g., "Buy ETH if RSI < 30"). We run the backtest and show you the win rate in seconds.
Roadmap (Coming Soon): 🚧 Automated Execution: Currently, we provide the trade signals and validation. Direct broker connection for auto-execution is our next priority.
📱 Mobile App: To receive real-time push notifications for the signals generated by your agent, download the app here
• iOS: https://apps.apple.com/app/id6754526355
• Android: https://play.google.com/store/apps/details?id=com.heytraders.mobile
Note: Your chat and strategies are fully encrypted and we never train on your data unless you opt-in.
I’d love your feedback: For those trading solo—what is the biggest pain point in trading crypto?
Thanks for checking us out! 🚀
HeyTraders
[UPDATE: 🚨 Live Support]
We are experiencing high traffic and shipping hotfixes in real-time! 👨💻
I'm fixing bugs as fast as possible.
If you encounter any issues, join our Live Telegram Channel for the fastest fix.
👉 Join here: https://t.me/heytradersofficial
instant backtesting is great, but slippage is the real killer in crypto. does the simulation engine account for exchange fees and liquidity, or is it just raw price data?
HeyTraders
@samet_sezer Thanks Samet, Great point. A backtest without friction costs is just a fantasy.
You are absolutely right. Here is how we handle it:
Currently: We set 5bps for exchange fees and an additional 5bps for slippage, but you can adjust these individually.
Roadmap: We are building a full "Real Market Mock" engine using orderbook snapshots. This will allow us to accurately simulate:
Fee Dynamics: Distinguishing between Taker Fees (Market Orders) and Maker Fees (Limit Orders).
Execution Logic: Calculating precise slippage based on order book depth vs. fill probability for limit orders.
Thanks for highlighting this—getting the simulation right is our top priority!
Huge congrats on the launch! 🚀 Turning natural language into verifiable crypto quant strategies is a powerful unlock for serious traders on PH.
HeyTraders
@zeiki_yu Hey Zeiki, thanks! We believe serious traders should focus on finding Alpha, not fixing bugs. Hope this helps you save time!
Congrats for the launch. Curious if this is for short-term trading or long-term investing. Does it consider company fundamentals and news?
HeyTraders
@liang_tang Thanks for the question, Liang.
Fundamentals: Currently, we are crypto-first. While we don't parse company fundamentals like corporate balance sheets yet, we can handle market fundamentals (News, Narratives, Macro). We plan to expand to Stocks later and integrate company-specific data (Earnings, P/E).
Time Horizon: The AI is agnostic, but since Crypto has a relatively short history compared to Stocks, it is statistically difficult to validate multi-year investing strategies. Therefore, our current engine works best for short-to-mid-term horizons.
The 'instant backtesting' part is what caught my eye because I always wonder if my ideas would have actually worked in the past. I wonder how far back the data goes does it test against years of market history or just the last few months of trends?
HeyTraders
@theaxx Hey Thea. I appreciate your interest.
We fetch historical data directly via Exchange API (Binance by default), so you can test against the entire history of a coin since its listing date.
One thing to note: while you can access years of history, the backtesting speed depends on the Timeframe. For example, downloading and processing 1m candles for several years will naturally take more time.
Instantly validate ideas is its biggest selling point. Being able to quickly view a strategy’s historical performance has greatly boosted my willingness to experiment with new ideas. That said, are the backtesting parameter settings (e.g., transaction fees, slippage) flexible enough to adapt to the actual market conditions of different cryptocurrency trading pairs?
HeyTraders
The idea is interesting, but in this case my first question is: “How accurate are the algorithm’s recommendations, and can it make mistakes?” The answers determine profits or losses.
HeyTraders