Recently predictive models based on the Choquet integral have been applied successfully in machine learning and multi criteria decision making context. The ability of the Choquet integral to capture non-linear dependencies and its comprehensibility make it a very appealing tool. Yet, its complexity is often a barrier to estimate model parameters. In fact, the number of monotonicity constraints grows exponentially as the number of feature increases. This study addresses a heuristic approach to learn parameters underlying the choquistic regression model. In this regard, this study compares the gain of the proposed approach versus the original formalism of the choquistic regression. In addition, the run-time comparison in the experimental study is presented.

最近，基于 Choquet 积分的预测模型已成功应用于机器学习和多标准决策环境中。Choquet 积分捕获非线性相关性的能力及其可理解性使其成为非常有吸引力的工具。然而，它的复杂性通常是估计模型参数的障碍。事实上，单调性约束的数量随着特征数量的增加呈指数增长。本研究提出了一种启发式方法来学习 choquistic 回归模型的基础参数。在这方面，本研究比较了所提出方法的收益与 choquistic 回归的原始形式主义。此外，还介绍了实验研究中的运行时间比较。