揭示人类随机决策偏差的可解释模型，发现行为模式可预测且具策略价值。
Beyond the Black Box: Interpretable Models of Human Randomisation Failures
- 用可解释模型分析人类重复或回避行为，捕捉决策规律。
- 8.4万次决策显示，自身近期行为历史是主要可预测信号。
- 频率跟踪提升有限，透明模型更利于理解人类非理性行为。
混合策略均衡预测独立同分布行为：过去动作不应帮助预测未来决策。然而，人类玩家系统性偏离此基准，在奥尼尔零和纸牌游戏中，这些偏离可通过黑箱序列模型（如LSTM）预测。本文探讨是否能通过透明替代模型实现同等预测力并揭示行为机制。基于2,802对玩家的84,060次决策，首先对比朴素模型与行为模型、可解释机器学习及深度学习模型；再评估先前工作修改版EWA模型，并利用LASSO诊断提出嵌套频率追踪扩展。结果表明，重复或回避行为，尤其是玩家对自己近期行动历史的管理，解释了绝大部分可解释且可被策略利用的信号，而频率追踪在样本外预测中贡献甚微。
原文摘要 · Abstract (English)
Mixed strategy equilibrium predicts i.i.d play: past actions should not help predict future decisions. Human players, however, systematically depart from this benchmark, and in O'Neill's zero sum card game, these departures can be predicted by black box sequence models such as LSTMs. This paper asks whether that predictive power can be achieved by transparent alternatives that also reveal the behavioural structure behind it. Using 84,060 decisions from 2,802 pairs, the analysis first benchmarks naive and behavioral models against interpretable machine learning and deep learning models, then evaluates the modified EWA specifications of prior work against these benchmarks and uses the LASSO diagnostics to motivate a further nested frequency tracking extension. The results show that repeat or avoid behavior, especially players' management of their own recent action histories, accounts for most of the interpretable and strategically exploitable signal, while frequency tracking adds little out of sample.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。