SIMBA:数据不平衡的强大和可通用的测量方法
Julie R Pivin-Bachler1, Egon L van den Broek1
1Information and Computing Sciences, Utrecht University, Utrecht 3584 CC, the Netherlands.
Patterns (New York, N.Y.)
|December 31, 2025
概括
现实世界的数据不平衡给机器学习 (ML) 带来了挑战. 我们引入了失衡状态 (SIMBA) 测量,它准确地量化了多类数据失衡,并优于现有指标.
科学领域:
- 机器学习 机器学习
- 数据科学数据科学数据科学
- 人工智能的人工智能
背景情况:
- 诸如健康和网络安全等领域的真实世界数据集经常表现出严重的阶级不平衡.
- 数据失衡会降低机器学习模型的性能,导致偏见的结果有利于多数阶级.
- 评估数据不平衡的真正影响需要强大而准确的测量技术.
研究的目的:
- 为了应对在机器学习中准确测量数据不平衡的挑战.
- 引入一个新的指标,失衡状态 (SIMBA),考虑数据分布和重叠.
- 评估SIMBA的有效性与现有的不平衡措施相比.
主要方法:
- 对现有的数据不平衡指标进行了全面审查.
- 拟议的失衡状况 (SIMBA) 度量被开发出来,包括数据分布和重叠.
- 通过5个机器学习模型和498个数据集 (428个合成,70个非合成) 与其他7个不平衡指标进行了比较.
主要成果:
- 与其他七项措施相比,SIMBA在量化多类数据不平衡方面表现优异.
- 不平衡指标和分类绩效之间的相关性分析证实了SIMBA的一致性.
- 通过使用20个复杂度指标进行进一步的分析,证实了SIMBA的表现优异.
结论:
- 不平衡状态 (SIMBA) 是量化多类数据不平衡的准确和有效措施.
- SIMBA考虑数据分布和重叠的能力提高了其对分类性能的预测能力.
- SIMBA提供了一个有前途的解决方案,以减轻机器学习应用程序中数据不平衡所带来的挑战.
相关概念视频
Measures of Central Tendency
20.1K
The "center" of a data set is also a way of describing location. The two most widely used measures of the "center" of the data are the mean (average) and the median. The words "mean" and "average" are often used interchangeably. The substitution of one word for the other is common practice. The technical term is "arithmetic mean" and "average" is technically a center location. However, in practice among non-statisticians,...
20.1K
Skewness
17.6K
The measures of central tendency calculated from a data set may not reveal much about its intrinsic distribution. If a plot is made of the data set’s values, the mean and the median may not only differ, but also the plot may have more values on one side of the central tendencies. Such a data set is said to be skewed towards that side.
The longer the tail of the plot on one side, the more skewed it is. The skewness of a data set’s values suggests that the measures of central tendency...
The longer the tail of the plot on one side, the more skewed it is. The skewness of a data set’s values suggests that the measures of central tendency...
17.6K
Wald-Wolfowitz Runs Test II
507
The Wald-Wolfowitz runs test, commonly referred to as the runs test, is a nonparametric test used to assess the randomness of ordered data. The test evaluates the number of runs, which are consecutive sequences of similar elements within the data. If the number of runs is significantly higher or lower than expected, the data is considered non-random, indicating a detectable pattern or structure.
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and 0s. In...
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and 0s. In...
507
One-Way ANOVA: Unequal Sample Sizes
6.6K
One-way ANOVA can be performed on three or more samples of unequal sizes. However, calculations get complicated when sample sizes are not always the same. So, while performing ANOVA with unequal samples size, the following equation is used:
6.6K
Sign Test for Nominal Data
356
The sign test is a nonparametric method used to evaluate hypotheses about the median of a single sample or to compare the medians of two related samples. The sign test is particularly useful when dealing with nominal data, which includes distinct categories without an inherent order, such as names, labels, and preferences. Nominal data restricts statistical analysis to evaluating population proportions rather than mean or median values that require continuous data.
For example, consider a...
For example, consider a...
356
Introduction to the Sign Test
1.3K
The sign test is an important tool in nonparametric statistics, offering a straightforward yet effective method for analyzing matched pairs, nominal data, or hypotheses concerning the median of a population. It transforms data points into positive or negative signs, avoiding the need for assumptions about data distribution and instead focusing on the direction of change. It is particularly valuable when data does not conform to the normal distribution requirements of many parametric tests. For...
1.3K


