Quantification represents the problem of predicting class distributions in a given target set. It also represents a growing research field in supervised machine learning, for which a large variety of different algorithms has been proposed in recent years. However, a comprehensive empirical comparison of quantification methods that supports algorithm selection is not available yet. In this work, we close this research gap by conducting a thorough empirical performance comparison of 24 different quantification methods. To consider a broad range of different scenarios for binary as well as multiclass quantification settings, we carried out almost 3 million experimental runs on 40 data sets. We observe that no single algorithm generally outperforms all competitors, but identify a group of methods including the Median Sweep and the DyS framework that perform significantly better in binary settings. For the multiclass setting, we observe that a different, broad group of algorithms yields good performance, including the Generalized Probabilistic Adjusted Count, the readme method, the energy distance minimization method, the EM algorithm for quantification, and Friedman's method. More generally, we find that the performance on multiclass quantification is inferior to the results obtained in the binary setting. Our results can guide practitioners who intend to apply quantification algorithms and help researchers to identify opportunities for future research.

中文翻译：

---

定量方法的比较评价

量化表示预测给定目标集中的班级分布的问题。它也代表了有监督机器学习领域的一个不断发展的研究领域，近年来，针对该领域提出了各种各样的算法。但是，尚无法提供支持算法选择的量化方法的全面经验比较。在这项工作中，我们通过对24种不同的量化方法进行全面的经验性能比较来缩小研究差距。为了考虑二进制和多类量化设置的各种不同场景，我们对40个数据集进行了将近300万次实验。我们观察到，没有哪一种算法能比所有竞争者都胜过其他算法，但要确定一组方法，包括中值扫描和DyS框架，它们在二进制设置中的性能要好得多。对于多类设置，我们观察到一组不同的算法产生了良好的性能，包括广义概率调整计数，自述方法，能量距离最小化方法，用于量化的EM算法和Friedman方法。更普遍地说，我们发现多类量化的性能不如在二元设置中获得的结果。我们的结果可以指导打算应用量化算法的从业人员，并帮助研究人员确定未来研究的机会。包括广义概率调整计数，自述文件方法，能量距离最小化方法，用于量化的EM算法和Friedman方法。更普遍地说，我们发现多类量化的性能不如在二元设置中获得的结果。我们的结果可以指导打算应用量化算法的从业人员，并帮助研究人员确定未来研究的机会。包括广义概率调整计数，自述文件方法，能量距离最小化方法，用于量化的EM算法和Friedman方法。更普遍地说，我们发现多类量化的性能不如在二元设置中获得的结果。我们的结果可以指导打算应用量化算法的从业人员，并帮助研究人员确定未来研究的机会。