Overview

Investment research has consistently endeavored to find innovative approaches for building efficient portfolios. My mission is to elevate traditional investment strategies by incorporating advanced techniques, ranging from network theory to machine learning and AI. These novel methods help uncover hidden patterns in financial markets, providing a fresh perspective on wealth allocation.

While Machine Learning and AI have recently become buzzwords in investment research and the broader financial industry, their roots trace back to earlier eras. For instance, Neural Networks, a foundational concept in AI, dates back to the work of McCulloch and Pitts in 1943. The evolution and adoption of these techniques were once hampered by computational limitations. But today, with modern devices boasting processing power that dwarfs even the computers of the Apollo era, the possibilities are boundless.

In my body of research, I harness these ML/AI tools to address pressing questions in investment research. Below are some of my notable works that demonstrate the application of these techniques in the realm of financial investments:

Key Research Works

Following Insiders with Jonathan Brogaard

• This work probes into the influence of insider trading activities on stock market behaviors, uncovering correlations and potential causations.

Machine Learning and the Stock Market with Jonathan Brogaard

• Delving into the capabilities of machine learning, this study investigates its applicability in predicting and analyzing stock market trends.

Optimal versus Naive Diversification: False Discoveries, Transaction Costs and Machine Learning

• This research contrasts different diversification strategies in investments, weighing their efficiency in the face of emerging machine learning models.