Intelligent Investing, a research-driven market analysis platform, posits that artificial intelligence can enhance financial forecasting by handling large datasets, speeding up strategy development, and enabling systematic execution. However, human interpretation is vital for providing the context necessary to translate data into meaningful market insights.
This philosophy is embodied by founder Arnout Ter Schure. Holding a PhD in environmental sciences and over a decade of scientific research experience, Dr. Ter Schure brings an analytical mindset to finance. His move to market analysis reflects a focus on data and patterns. He has developed proprietary indicators and a multi-layered framework combining technical, sentiment, and cyclical analysis, which offers context for his view on AI in financial decision-making.
“Financial markets are becoming more complex and fast-moving,” Ter Schure says, noting AI’s role in supporting traditional approaches. A study on multi-agent deep learning in financial markets shows modern AI systems excel in handling large data and pattern recognition, improving analytical efficiency in high-speed trading when combined with methodologies like the Elliott Wave principle.
AI’s role aligns with Ter Schure’s perspective of it as a strong analytical companion, particularly where speed and precision are needed. “AI excels when tasks are clear. Provided the structure, parameters, and objectives, it executes with remarkable speed and precision,” notes Ter Schure. This includes generating trading algorithms, coding strategies, and rapid backtesting over historical data.
As AI integrates more into analysis, its reliance on human-defined boundaries becomes clear. Ter Schure highlights that AI systems derive from human input—data, assumptions, frameworks—and require human-defined direction and purpose. “AI accelerates the ‘how,’ but a human defines the ‘why,’” he says, a crucial distinction in market analysis.
In forecasting, where interpretation is key, AI can outline patterns but lacks the ability to interpret them amidst structural changes or unique conditions, where past data offers little aid. Thus, interpretation of evolving conditions is as significant as computational power. For Ter Schure, forecasting involves holding multiple probabilities. AI assists in outlining scenarios but doesn’t determine outcomes: “Markets evolve through structure and behavior. Models highlight patterns, but real-time pattern development needs human judgment,” he explains.
AI’s interaction with human assumptions is vital, reflecting existing data and user input, shaping results through initial biases. Ter Schure cautions that, “If initial premises hold biases, outputs may reflect them. Analysts must question, refine, and interpret results.”
Financial markets, influenced by collective sentiment like optimism and caution, remain constant despite trading digitalization. While AI can identify past behaviors, understanding their current significance requires experience. Ter Schure’s methodology illustrates how structured human analysis complements technological tools, combining Fibonacci ratios and the Elliott Wave principle to interpret market cycles and map potential price movements. His method involves alternative scenarios for adaptability to evolving conditions, creating a continuously reassessing framework.
Though AI identifies patterns, interpreting complex wave structures requires human judgment. Multi-layered corrections depend on contextual understanding, where small variations affect interpretation.
Ultimately, Ter Schure suggests AI extends the analytical process, enhancing components while leaving interpretive decisions to analysts. AI’s task execution complements human judgment depth. “Technology expands our capabilities, but understanding dictates application. Meaningful progress lies in the combination,” he concludes.