Browse categories
Explore
Fiverr Pro
English
$
USD
I will build python trading systems for quantconnect
Quantitative Developer: Trading Systems from Research to Production
I build quantitative trading systems for professional traders, prop firms, hedge funds, asset managers, and fintechs, from alpha discovery through validation to production deployment. I turn market hy...
About this Gig
I develop quantitative trading systems in Python for QuantConnect, from research and validation to LEAN deployment.
I turn market hypotheses and discretionary rules into testable algorithms or refine existing strategies, code, and notebooks.
Scope may include data engineering, asset selection, signals and factors, statistical modeling, machine learning, portfolio construction, risk controls, and execution.
Validation may cover fees, slippage, realistic fills, liquidity analysis, out-of-sample and walk-forward testing, Monte Carlo, sensitivity, and regimes, with checks for overfitting, look-ahead bias, and data leakage.
For production projects, I prepare systems for paper or live trading on QuantConnect Cloud or local LEAN, with broker integration, automated tests, logging, and monitoring.
You receive modular source code, reproducible backtests, and a technical report with assumptions, findings, and limitations.
Research may lead to rejecting a hypothesis. Profitability is not guaranteed. NDA available.
Contact me before ordering to define scope, data, infrastructure, deliverables, and acceptance criteria.
Platform:
Custom
•
Binance
•
Other
Development technology:
Python
•
Cpp
•
Other
FAQ
Can you create, migrate, or improve a strategy on QuantConnect?
Yes. I turn hypotheses and discretionary rules into explicit Python/LEAN logic, migrate strategies from other platforms, or review existing code and notebooks. Scope may include signals, asset selection, portfolio construction, risk controls, and execution.
What is the difference between the packages?
Foundation: prototype, initial backtest, and report. Validation: modular system, robustness tests, risk, and paper trading readiness. Production: advanced validation, automated execution, monitoring, and deployment support. Scope and acceptance criteria are defined before ordering.
How do you validate strategies and make backtests more realistic?
I model fees, slippage, order execution, margin, and liquidity constraints. Tests may include out-of-sample, walk-forward, Monte Carlo, sensitivity, regimes, and stress, with checks for overfitting, look-ahead bias, and data leakage. I document assumptions and limitations.
Do you use machine learning on QuantConnect?
Yes, when supported by the hypothesis and data. I use scikit-learn, XGBoost, or PyTorch for prediction, classification, feature selection, text analysis, or regime detection. I compare against simpler models using out-of-sample tests, costs, and controls for temporal leakage.
Which markets and exchanges do you develop systems for?
U.S. stocks/ETFs; equity/index options; futures and futures options; FX, CFDs, spot crypto, and crypto futures. Exchanges: NYSE, Nasdaq, NYSE Arca/American, Cboe/CFE, CME, CBOT, COMEX, NYMEX, ICE, Eurex, HKFE/HKEX, KRX, and NSE/BSE. Coverage varies by asset, dataset, and connector.
Which brokers and execution platforms can you integrate?
LEAN connectors: IBKR, Charles Schwab, TradeStation, tastytrade, Alpaca, OANDA, Webull, Tradier, Public, Clear Street, Wolverine, Samco, Zerodha, Binance/Binance.US, Coinbase, Bitfinex, Bybit, Kraken, dYdX, Bloomberg EMSX/FIX, Trading Technologies, and SS&C Eze. Availability varies by environment.
Which data sources do you use with QuantConnect and LEAN?
QuantConnect datasets, broker feeds, and native integrations: Databento, Bloomberg BPIPE/Terminal Link, FactSet, Polygon, IQFeed, Theta Data, Alpha Vantage, Trading Technologies, and SS&C Eze. Market, fundamental, and alternative data, depending on dataset, subscription, and Cloud/local environment.
What technology stack do you use from research to production?
Python, QuantConnect/LEAN, QuantBook, Jupyter, pandas, NumPy, SciPy, Polars, and statsmodels. Local LEAN: LEAN CLI, Docker, Linux, SQL, Git, pytest, and CI/CD, with monitoring as needed. Deployment on QuantConnect Cloud or your own infrastructure, including AWS, Azure, or Google Cloud.
What do I need to provide to start the project?
Send your objective, assets, timeframe, hypothesis or rules, data, risk limits, broker, and existing code. Specify Cloud or local LEAN and research, paper, or live trading. Data, platform, and hosting costs are separate; ongoing support is contracted separately.
How do you handle communication and confidentiality?
I prioritize Fiverr chat and written documentation to keep communication clear and decisions traceable. Short Fiverr calls can help clarify requirements or demonstrate results. NDA available; your strategy, code, data, documentation, and results remain confidential.
