FISHNET: Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert Swarms, and Task Planning

TL;DR

FISHNET is a modular agentic architecture designed to generate financial intelligence from vast, heterogeneous data sources, overcoming limitations of traditional methods and large language models in financial analysis.

Contribution

The paper introduces FISHNET, a novel modular architecture that enhances financial insight generation through sub-querying, harmonizing, neural-conditioning, expert swarming, and task planning.

Findings

Achieves over 98,000 regulatory filings analysis

61.8% success rate in financial insight generation

Demonstrates the importance of each agent component

Abstract

Financial intelligence generation from vast data sources has typically relied on traditional methods of knowledge-graph construction or database engineering. Recently, fine-tuned financial domain-specific Large Language Models (LLMs), have emerged. While these advancements are promising, limitations such as high inference costs, hallucinations, and the complexity of concurrently analyzing high-dimensional financial data, emerge. This motivates our invention FISHNET (Financial Intelligence from Sub-querying, Harmonizing, Neural-Conditioning, Expert swarming, and Task planning), an agentic architecture that accomplishes highly complex analytical tasks for more than 98,000 regulatory filings that vary immensely in terms of semantics, data hierarchy, or format. FISHNET shows remarkable performance for financial insight generation (61.8% success rate over 5.0% Routing, 45.6% RAG R-Precision). We conduct rigorous ablations to empirically prove the success of FISHNET, each agent's importance, and the optimized performance of assembling all agents. Our modular architecture can be leveraged for a myriad of use-cases, enabling scalability, flexibility, and data integrity that are critical for financial tasks.