Scientific Trading Podcast

This episode is a deep dive into the paper by Jorge Faleiro defining Sigma, an open and domain-specific language designed to allow large-scale collaboration in economics, especially within financial trading and modeling. The paper is publicly available in the author’s arXiv.org page.This audio podcast is produced by the author using generative artificial intelligence technology, and the publicly available version of the Sigma paper as the main source. Get full access to Scientific Trading at jfaleiro.substack.com/subscribe

This episode explores the application of incremental learning, specifically using a Stochastic Gradient Descent (SGD) model, for building a robot trading system. It contrasts this approach with batch-supervised learning and reinforcement learning, arguing that incremental learning is more suitable for the non-stationary and rapidly changing nature of financial data. The article presents a simplified demonstration of how such a system can be built and trained, while also cautioning against over-optimistic expectations of guaranteed profit.This audio podcast is produced by the author using generative artificial intelligence technology, and the article describing the end-to-end process of developing the nowcasting model is used as the main source. Get full access to Scientific Trading at jfaleiro.substack.com/subscribe

Back in October 2019, J. Faleiro published an article on Substack, "The Legacy Trader is Dead. Long Live the Computational Trader," which examined a significant societal transition away from intuitive decision-making towards a purely quantitative, algorithm-driven approach. The article describes a significant shift in the financial trading landscape, comparing the decline of "legacy traders" to a mass extinction event, much like the dinosaurs' demise after the Chicxulub asteroid impact. These legacy traders, characterized by their reliance on intuition and traditional methods, have been largely replaced by a new breed: "computational traders." This transformation is attributed to the disruptive force of technology, which brought increased complexity, transparency, and efficiency to finance. Computational traders distinguish themselves through specialized knowledge spanning three critical domains: * Software engineering, for building robust and reliable trading systems; * Financial engineering, for understanding the intricate financial products and market mechanics; and * Data science, for leveraging of advanced analytical techniques to anticipate market behavior scientifically. Ultimately, the article argues that continuous adaptation and mastery of these interdisciplinary fields are essential for success in the evolving world of finance.The author accurately foresaw the rapid acceleration of this change, particularly in the realm of advanced algorithms like Large Language Models (LLMs) and other large-quantitative models. The piece served as a prescient warning, highlighting how these predicted technological advancements would dramatically impact the world by 2025. Get full access to Scientific Trading at jfaleiro.substack.com/subscribe