Motivated by the successes of deep learning, we propose a class of neural network-based discrete choice models, called RUMnets, inspired by the random utility maximization (RUM) framework. This model formulates the agents' random utility function using a sample average approximation. We show that RUMnets sharply approximate the class of RUM discrete choice models: any model derived from random utility maximization has choice probabilities that can be approximated arbitrarily closely by a RUMnet. Reciprocally, any RUMnet is consistent with the RUM principle. We derive an upper bound on the generalization error of RUMnets fitted on choice data, and gain theoretical insights on their ability to predict choices on new, unseen data depending on critical parameters of the dataset and architecture. By leveraging open-source libraries for neural networks, we find that RUMnets are competitive against several choice modeling and machine learning methods in terms of predictive accuracy on two real-world datasets.

翻译：受深度学习成功经验的启发，我们提出一类基于神经网络的离散选择模型——RUMnets，该模型灵感来源于随机效用最大化（RUM）框架。该模型利用样本均值逼近来形式化决策者的随机效用函数。我们证明，RUMnets能够精准逼近RUM离散选择模型类：任何源于随机效用最大化的模型，其选择概率均可由RUMnet任意精确逼近。反之，任意RUMnet均符合RUM原则。我们推导了基于选择数据拟合的RUMnets泛化误差上界，并从理论上揭示了其根据数据集与架构关键参数对未见数据预测能力的影响。通过利用神经网络开源库，我们在两个真实数据集上发现，RUMnet在预测精度上与多种选择建模及机器学习方法相比具有竞争力。