arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.16147cs.LGcs.MA
收藏

利用认知模型改进推荐中个体参与度的预测

Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models

Carnegie Mellon University(卡内基梅隆大学);Harvard University(哈佛大学)

Roderick Seow, Yunfan Zhao, Duncan Wood, Milind Tambe, Cleotilde Gonzalez

AI总结:

本文提出基于实例学习理论的认知模型,利用真实孕产妇健康数据改进个体行为动态预测,相比LSTM更准确,并能估计状态波动性与干预敏感性以提升其他模型训练效率。

摘要:

对于资源有限的公共卫生项目而言,预测行为如何随时间变化以及如何响应干预措施的能力,对于决定何时以及向谁分配干预措施至关重要。我们利用来自真实世界孕产妇健康项目的数据,展示了基于实例学习(IBL)理论的认知模型如何增强现有的纯计算方法。我们的研究结果表明,与通用时间序列预测器(如LSTM)相比,反映人类决策过程的IBL模型能够更好地预测个体状态的动态变化。此外,IBL还提供了对个体状态波动性及其对干预措施敏感性的估计,这可以提高其他时间序列模型的训练效率。

英文摘要:

For public health programs with limited resources, the ability to predict how behaviors change over time and in response to interventions is crucial for deciding when and to whom interventions should be allocated. Using data from a real-world maternal health program, we demonstrate how a cognitive model based on Instance-Based Learning (IBL) Theory can augment existing purely computational approaches. Our findings show that, compared to general time-series forecasters (e.g., LSTMs), IBL models, which reflect human decision-making processes, better predict the dynamics of individuals' states. Additionally, IBL provides estimates of the volatility in individuals' states and their sensitivity to interventions, which can improve the efficiency of training of other time series models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑