Seeking Collaborators — Building a Multi-Index Algorithmic Trading System for Synthetic Indices

Hello everyone,

I'm looking to connect with developers, quantitative researchers, algorithmic traders, and AI engineers interested in collaborating on an ambitious research and development project focused exclusively on synthetic indices.

Our vision

We want to build a multi-index algorithmic trading system capable of studying synthetic markets, discovering potential trading opportunities, testing different strategies, and adapting its approach to changing market conditions.

Rather than developing another conventional EA based on a fixed set of indicators, our goal is to create a research-driven trading ecosystem that combines quantitative analysis, automated experimentation, AI agents, and continuous market observation.

What we want to develop

1. Multi-Index Market Research

Study multiple synthetic indices across different timeframes, identify their statistical properties, analyze volatility regimes, price behavior, trends, reversals, and recurring market structures.

2. Automated Strategy Discovery

Develop a research engine capable of exploring different strategy families, generating hypotheses, testing alternative approaches, and identifying strategies that demonstrate statistically meaningful results.

3. AI-Powered Quantitative Research

Use AI agents and machine learning to assist with market analysis, strategy generation, experiment management, optimization, and research evaluation.

4. Autonomous Shadow Trading

Create independent shadow bots that monitor live synthetic markets and execute virtual trades without placing real orders. Each bot should independently manage virtual entries, Stop Loss, Take Profit, trade duration, and performance tracking.

5. Multi-Strategy and Multi-Index Architecture

Build a system capable of operating multiple strategies across several synthetic indices, identifying suitable market conditions and allocating research attention to promising opportunities.

6. Robust Testing and Validation

Implement historical backtesting, walk-forward analysis, out-of-sample validation, Monte Carlo simulations, transaction-cost modeling, and overfitting detection.

Technologies and expertise we are interested in

- Python, MQL5 and MetaTrader 5
- Quantitative finance and statistical analysis
- Algorithmic strategy development
- Machine learning and reinforcement learning
- AI agents and autonomous research systems
- Time-series analysis and data engineering
- Backtesting and paper/shadow trading infrastructure
- Software architecture and open-source development

Who can contribute?

We welcome experienced developers, independent traders, quantitative researchers, programmers, students, and anyone with relevant technical expertise.

You do not need to master every technology. We are interested in complementary contributions, including:

- Original strategy ideas and research proposals.
- Python or MQL5 modules.
- Statistical and mathematical analysis.
- AI agent development.
- Backtesting improvements.
- Shadow trading infrastructure.
- Technical reviews and reproducible experiments.

Our research principles

We do not assume that profitable strategies already exist. Every idea must be tested, evaluated, and challenged. Negative results are useful research findings, and no strategy will be considered successful based on a backtest alone.

This is an independent research initiative, not an offer of investment services or a claim of guaranteed returns. We are not affiliated with Deriv or any synthetic-index provider.

How to participate

If you are interested, please send us:

1. A brief introduction and your technical background.
2. Your relevant projects, GitHub profile, portfolio, or previous work.
3. The area where you would like to contribute.
4. Any research ideas, strategy proposals, or technical improvements you would like to suggest.

Contact: blezpite@gmail.com

We are looking for people who are genuinely interested in research, experimentation, and building something meaningful together.

Let's explore what we can accomplish through collaborative quantitative research.