About the Event
Held in March 2024, the AI-Based Trading Workshop 2024 brought together top minds in algorithmic and quantitative trading. This in-depth panel discussion explored how AI, machine learning, and generative technologies are reshaping strategy development, trading infrastructure, and the future of financial markets.
Speakers:
- Dr. Ernest Chan – Quantitative Trading Expert, Author, and Founder of PredictNow.ai
- Bert Mouler – CEO & Co-founder, Profluent Trading Group
- Stefan Jensen – CEO & Co-founder, Applied AI; Author of "Machine Learning for Algorithmic Trading"
- Mark Sison – Fidelity VIP Active Trader Specialist; EPAT Alumnus
What is the biggest impact of machine learning in financial markets today?
Bert Mouler:
Machine learning in finance has accelerated strategy development and execution. With generative AI, firms can automate tasks like parsing API documentation and onboarding new trading venues within weeks. This speed is crucial in fast-moving markets such as crypto, making AI a key tool for trading strategy automation.
How has generative AI (like ChatGPT) changed trading and strategy development?
Stefan Jensen:
Generative AI boosts productivity by streamlining software development, data processing, and document summarization. It's especially valuable for strategy development involving fundamental analysis, where summarizing large volumes of financial data is critical.
Dr. Ernest Chan:
Generative AI like GPT helps with drafting code for backtesting and strategy implementation. Though not always accurate, it saves significant time in early-stage development, making it a supportive tool for algorithmic trading.
Where is AI most useful in trading today?
Dr. Ernest Chan:
AI is most effective in risk management, asset allocation, and portfolio optimization. These are foundational aspects of trading where AI improves consistency and accuracy. As a form of corrective AI, it flags low-probability trades and aligns trading strategies with prevailing market regimes.
How can machine learning improve portfolio construction?
Dr. Ernest Chan:
Machine learning enables Conditional Portfolio Optimization by predicting optimal asset allocation. This helps traders systematically respond to market themes like tech rallies or commodity cycles, optimizing portfolios for better performance.
What is the best way for individual traders to use machine learning?
Stefan Jensen:
Retail traders should focus on refining an existing strategy with machine learning, not the other way around. Understand what works first, then use AI for optimization and automation. Machine learning is most effective when enhancing a proven edge.
How can individual traders get started with AI in trading?
Bert Moller:
Start with a clear edge—like the pattern that most equity index returns happen overnight. Build a simple strategy around that and then apply AI to optimize execution and risk controls. Affordable access to market data via APIs has made this easier than ever.
How does one transition from a non-technical background into AI-based trading?
Mark Sison:
Structured programs like EPAT help bridge the gap between finance and technology. With mentorship and practical projects, traders can develop skills in Python, data analysis, and algorithmic trading even without a prior technical background.
What is the future of AI in financial markets?
Dr. Ernest Chan:
AI will take on more discretionary trading roles by analyzing narratives, sentiment, and macroeconomic factors. In the future, generative AI will likely outperform human discretionary traders in specific market conditions.
Bert Moller:
Profluent Trading is already experimenting with AI that analyzes Twitter and financial news. These systems aim to automate sentiment analysis and detect meaningful market shifts faster than human traders.
Will AI replace human traders completely?
Stefan Jensen:
No. While AI in trading will become more powerful, markets evolve constantly. Human oversight, intuition, and creativity remain essential for navigating unexpected changes and developing new strategies.
Will AI level the playing field for retail traders?
Mark Sison:
AI tools are making portfolio optimization, asset allocation, and market analysis more accessible. While execution advantages remain with institutions, retail traders now have access to institutional-grade analytics through AI-powered platforms.
What aspects of trading are most influenced by AI?
Stefan Jensen:
Machine learning influences strategy development by enabling more effective research and testing. Algorithmic trading processes are increasingly automated, and generative AI accelerates code development and financial content summarization.
Can AI fully automate trading?
Dr. Ernest Chan:
Not yet. Current AI is best at augmenting trader decisions rather than fully automating them. It’s like a co-pilot—great at risk management, parameter tuning, and supporting decision-making in trading strategy automation.
What are some practical use cases of AI in trading?
Dr. Ernest Chan:
- Risk Management: AI assesses trade quality and flags high-risk trades.
- Portfolio Optimization: Adjusts capital allocation based on predicted outcomes.
- Parameter Tuning: Dynamically updates stop-losses and entry criteria based on market regimes.
Is machine learning useful for discretionary traders?
Stefan Jensen:
Yes. NLP and machine learning are helpful for digesting unstructured data like earnings reports and news. They complement human discretion by streamlining information processing.
What should retail traders focus on when using AI?
Stefan Jensen:
Start with strategy. Don’t rely on models alone. Focus on market inefficiencies and then use machine learning to fine-tune strategy development, risk management, and execution.
Bert Moller:
Retail traders should validate ideas like overnight returns using historical data. Once the idea is proven, AI can help enhance it through automation and dynamic parameter adjustments.
How can traders transition from traditional to AI-powered trading?
Mark Sison:
Adopt a structured learning approach. Tools like EPAT provide training in finance, machine learning in trading, and hands-on coding experience. Learning by doing builds the foundation for AI-powered strategy execution.
What role will AI play in trading five years from now?
Dr. Ernest Chan:
AI will likely handle more discretionary decisions, including narrative analysis and macro-sentiment modeling.
Bert Moller:
Sentiment-driven models using social media and news will become more accurate, leading to real-time adjustments in strategy development and asset allocation.
What are the biggest mistakes traders make when using AI?
Stefan Jensen:
The most common mistake is starting with data and models instead of a sound trading principle. Traders must understand why a strategy works before applying machine learning to optimize it.
How has access to trading data changed over time?
Bert Moller:
Data democratization has lowered the barrier to entry. "Fifteen years ago, options data cost $150,000 a year. Now it’s available via APIs for a few hundred dollars," making machine learning in finance more accessible for all.
How can traders balance human intuition with AI-driven decision-making?
Stefan Jensen:
AI and human intuition work best together. Use AI to manage data overload and streamline analysis, but rely on human judgment for high-level strategy development and adaptation in dynamic markets.
Conclusion
The insights from the AI-Based Trading Workshop 2024 make it clear: artificial intelligence and machine learning are not just buzzwords—they’re transforming how markets operate. From portfolio optimization and trading strategy automation to risk management and discretionary trading, AI is playing a co-pilot role for traders of all levels. However, one message was repeated by every expert: AI is most powerful when combined with human judgment, strategic thinking, and a clear understanding of the market. The future of trading isn’t human vs. machine—it’s human with machine.
Next Steps
Whether you're new to the world of AI in trading or looking to refine and apply advanced machine learning techniques, this structured learning path will help you grow your skills with clarity and purpose:
Begin with insightful articles that break down concepts and showcase real-world applications. These expert-written blogs are a perfect way to stay up to date with the latest in algorithmic trading, model deployment, and generative AI tools:
- Trading using LLM: Generative AI & Sentiment Analysis
- Automated Trading Systems: Architecture, Protocols, and Latency
- ChatGPT for Trading: Prompts, Strategies, and Insights
- Sentiment Analysis for Trading
Want to build practical skills through self-paced online courses? Try Quantra, These hands-on modules offer structured, modular learning to suit your pace:
- Quantitative Trading for Beginners – 8-Course Guide – Ideal for newcomers to quant trading.
- Trading with Machine Learning: Regression – A step-by-step application of regression models in trading.
- Artificial Intelligence in Trading – Advanced – Explore classification, regression, and model optimization.
- News Sentiment Trading Strategies – Learn NLP-driven sentiment extraction for trade signals.
- Advanced Algorithmic Trading Strategies with Machine Learning – Build robust ML strategies with ensemble and tree-based models.
- Machine Learning Strategy and Live Trading – Learn to deploy ML strategies in real-time markets.
For serious learners looking to gain a professional edge, the Executive Programme in Algorithmic Trading (EPAT®) is the most comprehensive offering. It covers everything from classical ML models and deep learning to reinforcement learning, Python, and real-world strategy implementation. Designed for professionals, EPAT includes mentoring, capstone projects, and placement support.
Connect with an EPAT career counsellor to discuss the right quant role for your background.