about

Michael A. Derrico is a quantitative finance analyst and Python engineer based in New York City. His work sits at the intersection of financial data engineering and applied statistical research — building production-grade pipelines, post-trade analytics frameworks, and machine learning systems tuned for the demands of live market environments.

He holds a B.S. in Finance with a FinTech concentration from Fordham University's Gabelli School of Business, where a 3.774 GPA reflected sustained rigor across financial modeling, statistical analysis, and applied ML coursework. His academic projects were not exercises in theory — they were built to produce answers that matter: how much did execution cost, which model generalizes cleanly, where does AI actually create institutional value.

At Slopeside Strategy, he designs agentic automation tools that streamline complex analytical workflows for financial professionals. Previously at Rearc, he built a Databricks pipeline for extracting market signals from financial news and social media — from raw text to structured Delta Lake datasets, at production fidelity.

His research has spanned execution quality measurement (Implementation Shortfall, VWAP slippage), multi-model ML benchmarking under forensic no-leakage constraints, pre-trade optimization under time and volume constraints, and the institutional economics of AI adoption at scale. He presented findings from JPMorgan Chase's AI/ML deployment landscape to both technical and executive audiences.

He is certified in Bloomberg Market Concepts and Alteryx Designer Core, and is an active member of the Databricks data and AI community — attending the Databricks Data + AI Summit in San Francisco, Data + AI World Tours in New York City, and a AI Days Washington DC.