Algorithm Generator and Optimization Research Application

The AGORA Initiative was formulated to provide an integrated platform for Research, Risk Assessment, and Portfolio Management. Central to this idea is a set of applications built on the ARGOS platform utilizing AIAX objects. In its simplest form, AGORA delivers an experience via Jupyter Notebooks in which every example and principle are linked to transparent computer code connected to the same data that top investment management firms use. The work initially began targeted at computer scientists and mathematicians attempting to learn applied finance principles such as risk analysis and portfolio management. Since then, it has been adapted to help those unfamiliar with programming, but who understand research, to learn to code with real-world examples and functional code.


In the 1990's at Columbia University, James Claus began the development of an integrated optimization and research platform utilizing open source code made available via the Systems Optimization Laboratory at Stanford University. This base structure was later adapted and implemented using IBM®'s proprietary CPLEX™ optimization suite.  This CPLEX™-based version has been implemented in numerous groups, including the world's largest institutional investor and data vendor. Looking to the next generation of optimization technology initiatives, the AGORA Initiative was launched to create a more generalized architecture in which optimizers could be utilized in a "pluggable" manner, allowing users to choose among proprietary and open source solutions. Understanding that risk assessment and portfolio management are best understood in the context of real problems, the AGORA Initiative has always used real market data for testing and refining algorithms specially designed to generate risk-adjusted returns or "alpha."

Risk Assessment and Portfolio Management

The core of the AGORA Initiative is composed of optimizers that form its "engines of analysis". Looking to applications outside of finance on areas of hard science and applied engineering, it became abundantly clear that the optimization use cases in finance had limited the development of the underlying technology. While there are numerous companies providing optimization technology in the financial industry, most “investment optimizers” focus on simple parameterization rather than in core technology development. Understanding the importance of the core technology advances occurring, the ULISSES Project® began to restructure its codebase in 2018 to utilize these innovations making special effort to integrate open source resources such as those available via Google OR Tools.

Alpha Generation and Research Applications

Built on top of core risk assessment, and portfolio management functions constructed utilizing optimizers, are research applications called and manipulated via GUIs and Python scripts with the purpose of simplifying research activities that were previously the domain of highly technical experts. The first research applications deployed in the AGORA Initiative have been applications developed by Rand Labs that allow users to seamlessly integrate and manipulate data that are mapped into the AIAX object store, effectively allowing users to refine and monitor complex algorithms designed to produce alpha continually. Originally built to help mathematicians and computer scientists understand finance, the core functionality of AGORA has been adapted to help researchers more easily accomplish and manage their core tasks of research and alpha exploration.