Crypto Treding Advanced Signal Bot System [Prototype]

একটি প্রোটোটাইপ ক্রিপ্টো ট্রেডিং বট যা Python (Flask) + HTML/CSS/JS দিয়ে তৈরি। এটি রিয়েল টাইম BTC/USDT মার্কেট দেখায়, ছোট ML-based প্রেডিকশন দেয় এবং Buy/Sell/Hold অ্যাডভাইস প্রদান করে।

---

Features

1. রিয়েল টাইম BTC/USDT মার্কেট গ্রাফ দেখাবে
2. লাস্ট ৩০ মিনিট / ২৪ ঘন্টা / ৩০ দিনের মার্কেট ট্রেন্ড দেখাবে
3. ৫ মিনিটের প্রেডিকশন দিবে (ML-based)
4. Buy / Sell / Hold অ্যাডভাইস দেখাবে

ML প্রেডিকশন একটি simple LSTM প্রেডিক্টর (simulation mode) ব্যবহার করে প্রোটোটাইপ তৈরি করা হয়েছে।

---

Project Structure

crypto_bot/ │ ├── backend/ │ ├── app.py # Flask server │ ├── ml_model.py # ML prediction (LSTM simulation) │ └── utils.py # Binance API + data processing │ ├── frontend/ │ ├── index.html │ ├── main.js │ └── style.css │ └── requirements.txt # Flask, pandas, numpy, tensorflow, websocket-client, requests, etc.

---

Requirements

requirements.txt:

Flask==2.3.2 requests==2.31.0 pandas==2.1.0 numpy==1.26.0 tensorflow==2.15.0 websocket-client==1.6.3

---

Backend

utils.py

Binance থেকে historical এবং live data আনার জন্য:

import requests
import pandas as pd

BASE_URL = "https://api.binance.com/api/v3"

def get_historical_klines(symbol="BTCUSDT", interval="1m", limit=1000):
    url = f"{BASE_URL}/klines?symbol={symbol}&interval={interval}&limit={limit}"
    data = requests.get(url).json()
    df = pd.DataFrame(data, columns=[
        "Open time", "Open", "High", "Low", "Close", "Volume",
        "Close time", "Quote asset volume", "Number of trades",
        "Taker buy base", "Taker buy quote", "Ignore"
    ])
    df["Close"] = df["Close"].astype(float)
    df["Open"] = df["Open"].astype(float)
    df["High"] = df["High"].astype(float)
    df["Low"] = df["Low"].astype(float)
    df["Volume"] = df["Volume"].astype(float)
    return df

def get_latest_price(symbol="BTCUSDT"):
    url = f"{BASE_URL}/ticker/price?symbol={symbol}"
    data = requests.get(url).json()
    return float(data['price'])


---

ml_model.py

Simple LSTM simulation (prototype):

import numpy as np
import random

def predict_next_price(last_prices):
    """Simple simulation: next price = current price + random small change"""
    current = last_prices[-1]
    change = current * random.uniform(-0.001, 0.001)  # ±0.1% variation
    next_price = current + change
    return next_price

def decision_advice(current_price, predicted_price):
    if predicted_price > current_price * 1.0005:
        return "BUY"
    elif predicted_price < current_price * 0.9995:
        return "SELL"
    else:
        return "HOLD"


---

app.py

Flask API:

from flask import Flask, jsonify, render_template
from utils import get_historical_klines
from ml_model import predict_next_price, decision_advice

app = Flask(__name__)

@app.route('/')
def index():
    return render_template('index.html')

@app.route('/api/market')
def market_data():
    df = get_historical_klines(limit=100)
    last_prices = df['Close'].tolist()
    current_price = last_prices[-1]
    predicted_price = predict_next_price(last_prices)
    advice = decision_advice(current_price, predicted_price)

    response = {
        "current_price": current_price,
        "predicted_price": predicted_price,
        "advice": advice,
        "last_30m": {
            "min": min(last_prices[-30:]),
            "max": max(last_prices[-30:]),
            "trend": last_prices[-1] - last_prices[-30]
        },
        "last_24h": {
            "min": min(last_prices[-1440:]),
            "max": max(last_prices[-1440:]),
            "trend": last_prices[-1] - last_prices[-1440]
        }
    }
    return jsonify(response)

if __name__ == '__main__':
    app.run(debug=True)


---

Frontend

index.html

<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Crypto Bot Prototype</title>
<link rel="stylesheet" href="style.css">
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
</head>
<body>
<h1>Crypto Bot Dashboard</h1>

<div>
  <p>Current BTC Price: <span id="current_price"></span> USD</p>
  <p>Predicted Next Price: <span id="predicted_price"></span> USD</p>
  <p>Advice: <span id="advice"></span></p>
</div>

<canvas id="priceChart" width="800" height="400"></canvas>

<script src="main.js"></script>
</body>
</html>


---

main.js

async function fetchMarketData() {
    const response = await fetch('/api/market');
    const data = await response.json();

    document.getElementById('current_price').innerText = data.current_price.toFixed(2);
    document.getElementById('predicted_price').innerText = data.predicted_price.toFixed(2);
    document.getElementById('advice').innerText = data.advice;

    // Update chart
    const prices = Array.from({length: 100}, (_, i) => data.last_30m.trend + i);
    const ctx = document.getElementById('priceChart').getContext('2d');
    if(window.priceChart){
        window.priceChart.data.datasets[0].data = prices;
        window.priceChart.update();
    } else {
        window.priceChart = new Chart(ctx, {
            type: 'line',
            data: {
                labels: prices.map((_, i) => i),
                datasets: [{
                    label: 'BTC Price (USD)',
                    data: prices,
                    borderColor: 'green',
                    tension: 0.3
                }]
            }
        });
    }
}

setInterval(fetchMarketData, 5000);  // 5 seconds update
fetchMarketData();


---

style.css

body {
    font-family: Arial, sans-serif;
    background-color: #1b1b1b;
    color: white;
    text-align: center;
}

canvas {
    margin-top: 20px;
    background-color: #2c2c2c;
}


---

✅ এই প্রোটোটাইপ রিয়েল টাইম মার্কেট দেখাবে, প্রেডিকশন দিবে, এবং Buy/Sell/Hold অ্যাডভাইস দেখাবে।