Adaptive Agents and Data Quality in Agent-Based Financial Markets

Paper: arXiv 2311.15974

Abstract

We present our Agent-Based Market Microstructure Simulation (ABMMS), an Agent-Based Financial Market (ABFM) that captures much of the complexity present in the US National Market System for equities (NMS). Agent-Based models are a natural choice for understanding financial markets. Financial markets feature a constrained action space that should simplify model creation, produce a wealth of data that should aid model validation, and a successful ABFM could strongly impact system design and policy development processes. Despite these advantages, ABFMs have largely remained an academic novelty. We hypothesize that two factors limit the usefulness of ABFMs. First, many ABFMs fail to capture relevant microstructure mechanisms, leading to differences in the mechanics of trading. Second, the simple agents that commonly populate ABFMs do not display the breadth of behaviors observed in human traders or the trading systems that they create. We investigate these issues through the development of ABMMS, which features a fragmented market structure, communication infrastructure with propagation delays, realistic auction mechanisms, and more. As a baseline, we populate ABMMS with simple trading agents and investigate properties of the generated data. We then compare the baseline with experimental conditions that explore the impacts of market topology or meta-reinforcement learning agents. The combination of detailed market mechanisms and adaptive agents leads to models whose generated data more accurately reproduce stylized facts observed in actual markets. These improvements increase the utility of ABFMs as tools to inform design and policy decisions.

Complexity vs Empirical Score

• Math Complexity: 4.0/10
• Empirical Rigor: 7.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper is heavily focused on implementing a complex agent-based simulation (ABMMS) with detailed market infrastructure (fragmentation, latency, auctions) and adaptive agents (meta-RL), which requires significant implementation and computational resources, warranting high empirical rigor. While it references standard microstructure models and agent behaviors, it lacks heavy mathematical derivations or novel theoretical proofs, keeping math complexity moderate.

Research Flowchart

  flowchart TD
  A["Research Goal: Improve ABFM Utility by Addressing<br>Microstructure & Agent Complexity"] --> B["Develop ABMMS with Realistic Market Structure"]
  B --> C{"Data Input: Historical NMS Data"}
  C --> D["Populate with Simple Agents<br>(Baseline)"]
  D --> E{"Compute Simulated Market Data"}
  E --> F["Populate with Adaptive<br>Meta-RL Agents"]
  F --> E
  E --> G["Analyze & Compare<br>Generated Data to Stylized Facts"]
  G --> H["Key Finding: Adaptive Agents & Detailed<br>Microstructure Improve Model Accuracy"]

Cited References (106)

1. Allocative efficiency of markets with zero-intelligence traders: Market as a partial substitute for individual rationality (1993)
2. Zero is Not Enough: On The Lower Limit of Agent Intelligence For Continuous Double Auction Markets (1997)
3. Minimal-intelligence agents for bargaining behaviors in market-based environments (1997)
4. Adaptive agents in a persistent shout double auction (1998)
5. Price formation in double auctions (1998)
6. High-performance bidding agents for the continuous double auction (2001)
7. Strategic sequential bidding in auctions using dynamic programming (2002)
8. Strategic bidding in continuous double auctions (2008)

0 of 106 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.