Paper: arXiv 2307.11846

Authors: Bryce Morsky, Fuwei Zhuang, Zuojun Zhou

Abstract

We study the roles of social and individual learning on outcomes of the Minority Game model of a financial market. Social learning occurs via agents adopting the strategies of their neighbours within a social network, while individual learning results in agents changing their strategies without input from other agents. In particular, we show how social learning can undermine efficiency of the market due to negative frequency dependent selection and loss of strategy diversity. The latter of which can lock the population into a maximally inefficient state. We show how individual learning can rescue a population engaged in social learning from such inefficiencies.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper employs advanced stochastic processes and evolutionary game theory with precise formulas for payoffs and imitation probabilities, placing it in high math complexity. However, it relies entirely on simulation results of a theoretical model with no real-world data, backtests, or implementation details, resulting in low empirical rigor.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Roles of Social & Individual Learning<br>in Minority Game Outcomes"] --> B["Data/Inputs:<br>Social Network Structure<br>Strategy Sets<br>Market Parameters"]
  B --> C["Methodology:<br>Agent-based Modeling<br>Simulations of:<br>Social Learning vs. Individual Learning"]
  C --> D{"Computational Process:<br>Iterative Game Rounds"}
  D --> E["Outcome A:<br>Social Learning leads to<br>Loss of Diversity & Efficiency"]
  D --> F["Outcome B:<br>Individual Learning rescues<br>Population from Inefficiency"]
  E --> G["Key Findings:<br>1. Social learning undermines market efficiency<br>2. Negative frequency dependent selection<br>3. Individual learning prevents inefficiency traps"]
  F --> G

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes to analyze how social and individual learning affect outcomes in the Minority Game model of a financial market, showing that social learning can reduce market efficiency while individual learning can mitigate these inefficiencies.

Source sentence
We study the roles of social and individual learning on outcomes of the Minority Game model of a financial market. We show how individual learning can rescue a population engaged in social learning from such inefficiencies.

Assumes 6

  • After each turn agents learn socially with probability ℓs or individually with probability ℓi. model
    Source sentence
    After every turn, agents will learn socially or individually with probabilities ℓs and ℓi, respectively.
  • Social learning occurs via pairwise imitation across a fixed social network. model
    Source sentence
    We consider the case where this imitation occurs across a social network. Once the graph is constructed, we assume that it remains fixed throughout the game.
  • The social network is represented by either a complete graph or an Erdős‑Rényi random graph constructed with edge probability p = d/N. model
    Source sentence
    Specifically, we construct complete graphs and Erd˝os-R´enyi random graphs where agents can only socially learn from agents with which they share an edge. To construct the Erd˝os-R´enyi random graphs, a pair of agents is connected with probability p = d/N, where d is the mean node degree.
  • Imitation probability follows a logistic (Fermi) selection function based on payoff differences. model
    Source sentence
    Once a focal agent has been paired with one of its neighbours on the social network to learn from, we simulate social learning using a logistic function (as used in previous research on social learning and evolutionary game theory literature where it is sometimes called Fermi selection [48, 50, 37, 38]): Pi→j(t) = 1 1 + exp(κ(min(πik(t)) −max(πjk(t)))),
Show 2 more
  • Agents know the true historic success of others’ strategy tables. model
    Source sentence
    Additionally, we have assumed that agents know the true historic success of others’ strategy tables.
  • No costs are associated with either social or individual learning. other
    Source sentence
    For one, we have not assumed any costs associated with either social or individual learning.

Data

  • Synthetic Minority Game simulations synthetic unknown
    Source sentence
    After every turn, agents will learn socially or individually with probabilities ℓs and ℓi, respectively. 3 Results We begin our results by depicting several informative time series of the attendance A(t) in Figure 1.

Costs

Unclear - sources disagree The platform classifier and the paper-text extraction give different answers, so no value is asserted.

Platform classifier: Not applicable

Paper text extraction: Not modeled

Source sentence (the authors' words)
For one, we have not assumed any costs associated with either social or individual learning.

Finds 5

  • Social learning alone leads to large swings in attendance and high volatility, reducing market efficiency. theoretical
    Source sentence
    Social learning, however, on its own results in large swings in the population from buying to selling and thus a high volatility relative to the other cases (Figure 1c).
  • Social learning causes a crash in strategy‑table diversity, potentially locking the population into a maximally inefficient state. theoretical
    Source sentence
    This phe-nomenon occurs because there is a crash in strategy table diversity as agents lose strategy tables 5 (a) No social or individual learning, N = 1001 (b) Only individual learning, N = 1001 (c) Only social learning, N = 1001 (d) Individual and social learning, N = 1001 (e) Only social learning, N = 101 Figure 1: Time series of the attendance A for no individual or social learning (a), only individual learn-ing
  • Individual learning alone yields marginally lower attendance variability compared to no learning. theoretical
    Source sentence
    We find that when there is only individual learning, the variability in attendance is marginally lower than in the case with no social or individual learning (Figure 1b).
  • Adding individual learning to social learning reduces volatility to levels comparable to the no‑learning case. theoretical
    Source sentence
    Figure 1d depicts a representative example showing that the addition of indi-vidual learning reduces the volatility to levels comparable to the case where there is no learning (Figure 1a).
  • Individual learning can rescue a population from the inefficiencies caused by social learning. theoretical
    Source sentence
    We show how individual learning can rescue a population engaged in social learning from such inefficiencies.

Checked by others

Contradicted by

  • Market-Dependent Communication in Multi-Agent Alpha Generation (2025)
    On the question: Does information sharing affect strategy diversity in multi‑agent market games?
    Compare the findings

    This paper: Social learning causes a crash in strategy‑table diversity, potentially locking the population into a maximally inefficient state.

    That paper: All organizational structures converge to similar strategy correlations regardless of information sharing, eliminating diversity loss.

    A reports a crash in diversity due to social learning, while B reports no diversity loss as all structures converge, contradicting A.

Code

https://github.com/bmorsky/minority-games — the authors' own repository

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.