摘要翻译：
虽然研究人员越来越多地使用深度神经网络(DNN)来分析个体选择，但过拟合和可解释性问题仍然是理论和实践中的障碍。利用统计学习理论，本研究提出了一个框架来检验估计误差与近似误差之间的权衡，以及预测损失与解释损失之间的权衡。通过将解释损失度量定义为真实选择概率函数与估计选择概率函数之间的差值，将DNN在选择分析中的可解释性操作化。本研究还利用统计学习理论对DNN的预测损失和解释损失的估计误差进行了上界，揭示了DNN不存在过拟合问题的原因。然后对三种情况进行了仿真，将DNN与二进制logit模型(BNL)进行了比较。我们发现DNN在大多数场景的预测和解释方面都优于BNL，更大的样本容量释放了DNN的预测能力，而BNL则没有。基于2017年全国家庭出行调查(NHTS2017)数据集，运用DNN分析出行目的和出行方式的选择。实验结果表明，由于DNN具有内在的效用解释、适应多种信息格式的灵活性和自动学习效用规范的能力，它可以用于需求预测以外的选择分析。DNN比BNL具有更好的预测性和解释性，除非建模者对选择任务有完整的知识，并且样本量很小。总体而言，统计学习理论可以为今后在非渐近数据环境下的研究或在选择分析中使用高维统计模型奠定基础，实验表明DNN在政策和行为分析中的广泛应用是可行和有效的。
---
英文标题：
《Deep Neural Networks for Choice Analysis: A Statistical Learning Theory
  Perspective》
---
作者：
Shenhao Wang, Qingyi Wang, Nate Bailey, Jinhua Zhao
---
最新提交年份：
2019
---
分类信息：

一级分类：Economics        经济学
二级分类：General Economics        一般经济学
分类描述：General methodological, applied, and empirical contributions to economics.
对经济学的一般方法、应用和经验贡献。
--
一级分类：Quantitative Finance        数量金融学
二级分类：Economics        经济学
分类描述：q-fin.EC is an alias for econ.GN. Economics, including micro and macro economics, international economics, theory of the firm, labor economics, and other economic topics outside finance
q-fin.ec是econ.gn的别名。经济学，包括微观和宏观经济学、国际经济学、企业理论、劳动经济学和其他金融以外的经济专题
--

---
英文摘要：
  While researchers increasingly use deep neural networks (DNN) to analyze individual choices, overfitting and interpretability issues remain as obstacles in theory and practice. By using statistical learning theory, this study presents a framework to examine the tradeoff between estimation and approximation errors, and between prediction and interpretation losses. It operationalizes the DNN interpretability in the choice analysis by formulating the metrics of interpretation loss as the difference between true and estimated choice probability functions. This study also uses the statistical learning theory to upper bound the estimation error of both prediction and interpretation losses in DNN, shedding light on why DNN does not have the overfitting issue. Three scenarios are then simulated to compare DNN to binary logit model (BNL). We found that DNN outperforms BNL in terms of both prediction and interpretation for most of the scenarios, and larger sample size unleashes the predictive power of DNN but not BNL. DNN is also used to analyze the choice of trip purposes and travel modes based on the National Household Travel Survey 2017 (NHTS2017) dataset. These experiments indicate that DNN can be used for choice analysis beyond the current practice of demand forecasting because it has the inherent utility interpretation, the flexibility of accommodating various information formats, and the power of automatically learning utility specification. DNN is both more predictive and interpretable than BNL unless the modelers have complete knowledge about the choice task, and the sample size is small. Overall, statistical learning theory can be a foundation for future studies in the non-asymptotic data regime or using high-dimensional statistical models in choice analysis, and the experiments show the feasibility and effectiveness of DNN for its wide applications to policy and behavioral analysis.
---
PDF链接：
https://arxiv.org/pdf/1810.10465