This inventor holds 1 USPTO granted patent and 8 published patent applications. Top assignee: Fmr Corp.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Niyu Jia and Machine Learning for Portfolio Simulation.
Introduction
Niyu Jia is an inventor based in Revere, Massachusetts, and is associated with FMR Corp. His patent work applies machine learning to portfolio simulation and optimization.
Latest Patents
Jia is named on 1 patent: “Machine Learning Portfolio Simulating and Optimizing Apparatuses, Methods and Systems.” The invention processes requests for machine-learning simulations, decision-tree ensemble training, expected-return calculations, portfolio construction, scenario construction, and portfolio-return visualization.
The system uses neural networks as an encoder to generate latent variables and as a decoder to simulate market scenarios. A transfer layer between the encoder and decoder allows the latent variables to represent different distributions and dependency structures. The resulting simulated scenarios are designed to reflect the dynamic dependencies and volatility of historical market risk factors.
Career Highlights
Jia’s patent describes a machine-learning framework for modeling market scenarios and supporting portfolio analysis. Its components connect simulation and training processes with expected-return calculations, portfolio construction, and visualization.
Collaborations
The provided information identifies Aaron Gao and Samarjit Walia as Jia’s coworkers. It does not specify their roles in the patent or the invention.
Conclusion
Niyu Jia’s patent presents an integrated approach to portfolio simulation that uses neural networks and flexible latent-variable modeling to represent market behavior.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
