17/06/2026
We believe the future of AI must be explainable, attributable, and hallucination-free. Today we're excited to share our latest step toward that goal. 🧠📊 We've just published our second AI/Machine Learning manuscript:
Filter Before You Solve: A Deterministic-First / Learned-Second Architecture for AI-Driven Portfolio Management with Real-Money Training-Investment Calibration
👉 Read, download, and share it here: https://www.preprints.org/manuscript/202606.1287
What's inside? A deterministic-first / learned-second AI/ML framework currently deployed in regulated retail brokerage accounts. Two-stage calibration combines historical back-testing with live recalibration via continuous position snapshots. For full attribution, the framework's explainability layer uses SimDec — a global sensitivity analysis method — to identify the most influential portfolio components.
🌟 Also making waves: our first AI/ML manuscript, Decomposing the Theta Cliff, is in the final stages of peer review at MDPI.
Preprint: https://www.preprints.org/manuscript/202605.1985
MDPI Special Issue: The Use of Artificial Intelligence in Business: Innovations, Applications and Impacts:
https://www.mdpi.com/journal/ai/special_issues/800083VW91
We've open-sourced our research because we believe in collaborating globally: with universities, banks, hospitals, governments, businesses, AI innovation hubs, and our loyal customers around the world. The community feedback has been incredible so far. Dive in, review, share and let us know what you think below. 💬👇
