You will get an Autonomous Quantitative Trading Research & Backtesting System
Project details
I build quantitative research and backtesting systems that combine Python, kdb+/q, and MCP-connected tooling to turn trading ideas into measurable research results. My approach focuses on systematic strategy testing, performance and risk analysis, and reproducible research rather than generic ML solutions. For more advanced projects, I can extend this workflow into automated strategy research and iteration.
Machine Learning Tools
pandas, PythonWhat's included
| Service Tiers |
Starter
$75
|
Standard
$199
|
Advanced
$399
|
|---|---|---|---|
| Delivery Time | 3 days | 5 days | 10 days |
Number of Revisions | 1 | 2 | 2 |
Number of Model Variations | 1 | 2 | 3 |
Number of Scenarios | 1 | 2 | 3 |
Number of Graphs/Charts | 3 | 6 | 10 |
Model Validation/Testing | |||
Model Documentation | |||
Data Source Connectivity | - | ||
Source Code |
Optional add-ons
You can add these on the next page.
Additional Revision
+$25
Additional Model Variation
(+ 1 Day)
+$40
Additional Scenario
(+ 1 Day)
+$30About Bhawna
Quantitative Researcher | Python, Q/kdb+, ML & Backtesting
Ghaziabad, India - 3:02 pm local time
I work primarily with Python, Q/kdb+, Pandas, NumPy, scikit-learn, PyTorch, and TensorFlow, with hands-on experience building research and backtesting systems from hypothesis through evaluation.
My recent work includes an autonomous strategy iteration system integrating an LLM agent, Python backtesting engine, and persistent kdb+ research history. I built a vectorized backtesting engine covering 1,000+ trading days with transaction-cost modeling and Sharpe ratio, drawdown, and win-rate analytics. In one autonomous research run, the system improved Sharpe from 0.67 to 1.27 (+90%) while reducing maximum drawdown from 31% to 18%.
I also have experience in time-series forecasting, using Prophet, SARIMA, and XGBoost, as well as large-scale data analysis, machine learning, and production-oriented engineering.
I can help with:
• Quantitative research and strategy development
• Python backtesting systems
• Q/kdb+ data and research workflows
• Strategy performance analysis
• Time-series forecasting
• Financial/market data analysis
• Feature engineering and ML modeling
• Statistical analysis and model evaluation
• Research automation and experiment pipelines
I care about reproducible research, avoiding lookahead bias, rigorous validation, and understanding why a strategy works-not just optimizing a backtest.
If you have a strategy idea, market dataset, research problem, or backtesting workflow you'd like to develop or improve, feel free to reach out.
Steps for completing your project
After purchasing the project, send requirements so Bhawna can start the project.
Delivery time starts when Bhawna receives requirements from you.
Bhawna works on your project following the steps below.
Revisions may occur after the delivery date.
Review Strategy & Data
Review your strategy rules, historical data, objectives, and requirements to define the backtesting approach.
Prepare Quant Research Environment
Prepare the data and configure the strategy, parameters, benchmark, transaction costs, and backtesting methodology.