Browse categories
Explore
Fiverr Pro
English
$
USD
I will build quantitative trading systems in python for quantconnect
Quantitative Developer: Research, Backtest and Deploy Trading Systems
I work with professional traders, prop firms, hedge funds, managers and fintechs to research, validate, and develop quantitative trading systems—from alpha discovery to production deployment. I turn m...
Level 2
Has met high performance criteria and has a proven track record for meeting client expectations.
About this Gig
I turn market hypotheses, discretionary strategies, and existing algorithms into professional-grade quantitative systems on QuantConnect, designed with research rigor, robust architecture, and production-oriented engineering.
I develop in Python and the LEAN Engine, covering the full cycle: research, validation, engineering, deployment, and monitoring.
Scope can include data preparation, signal and factor research, feature engineering, statistical modeling, machine learning, portfolio construction, realistic backtesting, out-of-sample validation, walk-forward analysis, Monte Carlo, sensitivity analysis, market regimes, costs, slippage, risk controls, and execution logic.
On the production side, I can include modular architecture, brokerage, data, and API integrations, configuration, testing, logging, failure handling, deployment workflows, paper or live trading readiness, and technical documentation.
My process prioritizes clean code, auditable assumptions, reproducibility, and the prevention of overfitting, look-ahead bias, and data leakage.
I do not promise financial results. I deliver rigorous research, professional engineering, and transparent evidence.
Platform:
Custom
•
Binance
•
Other
Development technology:
Python
•
Cpp
•
Other
FAQ
What can you build on QuantConnect?
I can develop anything from an initial LEAN strategy to a complete quantitative system, including research, backtesting, validation, risk, execution, testing, documentation and, depending on scope, paper trading and deployment.
What is the difference between the packages?
Foundation: LEAN strategy with applied research, initial backtest, and report. Validated: modular architecture, robust validation, risk, and paper trading. Production: advanced validation, automation, observability, and assisted deployment. I confirm scope before the order.
Can you build a strategy from an idea or improve an existing one?
Yes. I can convert a market hypothesis or discretionary approach into testable rules, or review, refactor, and extend existing QuantConnect algorithms, Python models, and notebooks. Scope can cover research, validation, architecture, implementation, and production.
How do you make backtests more realistic and robust?
I model fees, spreads, slippage, fills, liquidity, capacity, order types, and brokerage rules. Depending on the package, I apply out-of-sample, walk-forward, Monte Carlo, sensitivity, regime, and stress tests to assess performance across different market and execution conditions.
Which markets and exchanges do you work with?
I work with US equities/ETFs, options, futures, and futures options (NYSE, Nasdaq, Cboe, CME Group, and ICE), plus forex, CFDs, indices, and crypto via Binance, Bybit, OKX, and Coinbase. Fixed income and other exchanges depend on the dataset, brokerage, and integration.
Which brokers, infrastructure, and data sources can you integrate?
Depending on the asset and environment, I integrate IBKR, TradeStation, Alpaca, Tradier, Binance, Bybit, OKX, Coinbase, Bloomberg EMSX, Trading Technologies, and FIX. Data: QuantConnect, Databento, Polygon, FactSet on local LEAN, or custom data/APIs. External licenses and costs not included.
What do I need to send before the project starts?
Send assets, timeframe, hypothesis or rules, data source, risk limits, cost and execution assumptions, brokerage, and deployment goal. Include any existing code, notebooks, reports, and results. With that, I confirm the package, scope, and deliverables.
What is your technical stack and how do you use AI?
I develop with Python, QuantConnect/LEAN, Research Environment, LEAN CLI, pandas, NumPy, statsmodels, scikit-learn, XGBoost, and PyTorch. Production: Git, Linux, Docker, SQL, testing, APIs, and CI/CD. I use ML, deep learning, or NLP only when the data, hypothesis, and validation justify it.
Do you guarantee profits or live performance?
No. I do not guarantee profit, returns, win rate, or future performance. I deliver rigorous research, reproducible backtests, validation, risk controls, technical implementation, and transparent evidence to support development and deployment decisions.
How do you handle communication and confidentiality?
Communication happens primarily through Fiverr chat and written documentation, preserving accuracy, traceability, and auditable decisions. Short calls can be used for alignment or demos. I can work under NDA; strategy, code, data, documentation, and results stay confidential.
