FreelanceSezioni

Best bot

MQL5 Esperti Python

Specifiche

import json
import os
import time

# Install via: pip install google-genai
from google import genai
from google.genai import types

class GeminiProTradingBot:
    """
    Automated Pro Trading Bot using Gemini API for AI-driven technical and trend analysis.
    """
    def __init__(self, symbol: str = "BTC/USDT", min_confidence: float = 0.75):
        self.symbol = symbol
        self.min_confidence = min_confidence
        # Initializes client using the standard GEMINI_API_KEY environment variable
        self.client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY"))

    def _build_system_instruction(self) -> str:
        return (
            "You are an expert quantitative trading algorithm. Analyze the provided OHLCV candle data "
            "and technical indicators. Output a strict JSON signal evaluating market state, "
            "recommendation (BUY, SELL, HOLD), confidence score (0.0 to 1.0), and risk management parameters."
        )

    def analyze_market(self, market_payload: dict) -> dict:
        """
        Sends formatted candle data to Gemini and returns structured trading signals.
        """
        prompt = f"""
        Analyze the following market state for asset: {self.symbol}
        
        Recent Candles (OHLCV) & Indicators:
        {json.dumps(market_payload, indent=2)}

        Determine the immediate market direction, entry price target, stop loss, and take profit levels.
        """

        # Define JSON Schema enforce exact AI response parameters
        response_schema = {
            "type": "OBJECT",
            "properties": {
                "action": {"type": "STRING", "enum": ["BUY", "SELL", "HOLD"]},
                "confidence": {"type": "NUMBER"},
                "reasoning": {"type": "STRING"},
                "target_entry": {"type": "NUMBER"},
                "stop_loss": {"type": "NUMBER"},
                "take_profit": {"type": "NUMBER"},
                "risk_reward_ratio": {"type": "NUMBER"}
            },
            "required": ["action", "confidence", "reasoning", "stop_loss", "take_profit"]
        }

        try:
            response = self.client.models.generate_content(
                model="gemini-2.5-flash",
                contents=prompt,
                config=types.GenerateContentConfig(
                    system_instruction=self._build_system_instruction(),
                    response_mime_type="application/json",
                    response_schema=response_schema,
                    temperature=0.2, # Low temperature for deterministic risk evaluation
                ),
            )
            return json.loads(response.text)
        except Exception as e:
            print(f"[Error] Gemini AI API query failed: {e}")
            return {"action": "HOLD", "confidence": 0.0, "reasoning": "API execution error."}

    def execute_signal(self, signal: dict):
        """
        Validates confidence thresholds and triggers simulated or real execution.
        """
        action = signal.get("action")
        confidence = signal.get("confidence", 0.0)

        print("\n--- [AI SIGNAL RECEIVED] ---")
        print(f"Action: {action} | Confidence: {confidence * 100:.1f}%")
        print(f"Reasoning: {signal.get('reasoning')}")
        
        if confidence < self.min_confidence or action == "HOLD":
            print("Status: Execution skipped (Insufficient confidence or HOLD signal).")
            return

        print(f"Status: EXECUTING {action} ORDER")
        print(f"Entry Price Target : {signal.get('target_entry')}")
        print(f"Stop Loss Target    : {signal.get('stop_loss')}")
        print(f"Take Profit Target  : {signal.get('take_profit')}")
        # Place broker API execution call here (e.g., CCXT, MetaTrader, or exchange REST APIs)


# --- Example Run ---
if __name__ == "__main__":
    # Mock OHLCV candle feed with RSI & MACD indicators
    sample_market_data = {
        "timeframe": "5m",
        "current_price": 64250.00,
        "rsi_14": 28.5, # Oversold
        "macd": {"macd_line": -120.4, "signal_line": -145.2, "histogram": 24.8},
        "recent_candles": [
            {"close": 64500, "volume": 12.4},
            {"close": 64350, "volume": 18.1},
            {"close": 64100, "volume": 25.6},
            {"close": 64250, "volume": 32.0}
        ]
    }

    bot = GeminiProTradingBot(symbol="BTC/USDT", min_confidence=0.70)
    signal = bot.analyze_market(sample_market_data)
    bot.execute_signal(signal)

Con risposta

1
Sviluppatore 1
Valutazioni
Progetti
0
0%
Arbitraggio
0
In ritardo
0
Gratuito
2
Sviluppatore 2
Valutazioni
(64)
Progetti
144
46%
Arbitraggio
20
40% / 20%
In ritardo
32
22%
Gratuito
3
Sviluppatore 3
Valutazioni
Progetti
0
0%
Arbitraggio
0
In ritardo
0
Gratuito
4
Sviluppatore 4
Valutazioni
(1)
Progetti
1
0%
Arbitraggio
1
0% / 100%
In ritardo
0
Gratuito
5
Sviluppatore 5
Valutazioni
(1)
Progetti
1
0%
Arbitraggio
1
0% / 0%
In ritardo
0
In elaborazione
6
Sviluppatore 6
Valutazioni
Progetti
0
0%
Arbitraggio
0
In ritardo
0
Gratuito
7
Sviluppatore 7
Valutazioni
(2)
Progetti
2
50%
Arbitraggio
0
In ritardo
0
Gratuito
8
Sviluppatore 8
Valutazioni
Progetti
0
0%
Arbitraggio
0
In ritardo
0
Gratuito
9
Sviluppatore 9
Valutazioni
Progetti
0
0%
Arbitraggio
0
In ritardo
0
Gratuito
Ordini simili
Find out strategy based on 100 trade. 30+ USD
Hi, can you define entry conditions based on 100 or 200 trades? If you need more history, i can give you more trades. It is EURUSD with great results! If you can do it, contact me
I buy EA for USDEUR or XAUUSD for FTMO with proven backtest 30+ USD
I buy EA for USDEUR or XAUUSD for FTMO with proven backtest. Send me images with backtest reports where daily max dd is 1% on 200k account. I can buy several eas if you have them with proofs. Need images of backtesting for 5 years
MT5 Cloud Trade Copier Developer Needed 30+ USD
I am looking for an experienced developer to build a cloud-based MT5 trade copier . Requirements: One master MT5 account sends trades to multiple client MT5 accounts. Clients must not need to install an EA or run MT5/VPS themselves . Client accounts should connect using MT5 login, trading password and broker server. Copy market orders, pending orders, SL/TP changes, partial closes and full closes. Support risk/lot
EA really with the martingala system 30+ USD
i need someone that can make me an EA really easy with the martingala system?, I am looking for something that doesn't exceed 5 trades for the martingale, I think I did it, but it only works for propfirms, So i need to develop it on ninja trader I have identified a very very simple strategy but it only works on propfirms, with only two propfirm accounts, i absolutely need account A and account, And they have to open
I need somone who have a proven EA for MT5, suitable for live accounts and prop firms, including the Brazilian market? 30+ USD
Hi, do you have a proven EA for MT5, suitable for live accounts and prop firms, including the Brazilian market? I’m looking for ready, tested EAs. Can you send a backtest or demo? Please if you do have and can send me nacktest or demo you should Message me
AI Decision-System Developer for Existing MT5 Commander - No EA Build 30 - 100 USD
Access and confidentiality restrictions: You will receive only a separately named copy of the Commander . Existing trading EAs, presets, account credentials, Telegram credentials and proprietary entry/exit code will not be shared. The Commander intelligence must be developed using: Defined signal/input interfaces Anonymized historical logs and replay data Mock EA signals and test harnesses Documented authority and
Senior Algorithmic Trader / MQL4/MQL5 Developer for Custom SMC, ICT & HFT Scaled Trading Bot 30 - 500 USD
We are looking for an expert algorithmic trading developer to build a high-performance, fully automated Custom Expert Advisor (EA) or trading bot. The bot must integrate advanced Smart Money Concepts (SMC) , Inner Circle Trader (ICT) methodologies, and Volume Spread Analysis (VSA) with a high-frequency trading (HFT) style execution and scaling model. The core objective is to program a bot that identifies
EA: Smart Break-Even & Partial Close Manager 30 - 200 USD
Develop an Expert Advisor for MetaTrader 5 that manages existing positions. Features Automatically detect all open positions. Apply Break-Even after price reaches a configurable profit. Partial Close: Close X% of volume at the first target. Move Stop Loss to Break-Even. ATR Trailing Stop (optional). Magic Number filter. Comment filter. Symbol filter. Trading session filter. Retry mechanism for trade operations
An expert adviser based on MQL5 30+ USD
Requirements Specification Here is an example of Requirements Specification for the development of the MACD Sample Expert Advisor, which is available in the MetaTrader 5 standard package. 1. The idea of the trading system is as follows : market entries are performed when MACD's main and signal lines intersect in the current trend direction . 2. Trend is determined based on the Exponential Moving Average with
JazzDaBot 30+ USD
""" Wick Reversal Strategy — core logic ===================================== Rules (as specified): - Timeframe: 15-minute candles - Entry: candle wick >= WICK_MULTIPLIER x body -> signal candle - long lower wick -> enter LONG at next candle's open - long upper wick -> enter SHORT at next candle's open - Exit: an opposite-direction wick candle forms while in a position - Stop-loss: just beyond the signal candle's

Informazioni sul progetto

Budget
50+ USD
Scadenze
da 1 a 30 giorno(i)

Cliente

Ordini effettuati1
Numero di arbitraggi0