|
AUTHOR(S): Ghazi Alkhatib
|
TITLE |
 PDF |
ABSTRACT The objective of this paper is to explore the use of statistical techniques for testing the hypothesis of machine learning (ML) metrics. These include accuracy, precision, recall, and F1 score. Understanding the interrelationship among them, as well as the confusion matrix, specificity, and sensitivity. The research methodology involved developing a taxonomy of factors affecting machine learning testing, such as supervised vs. unsupervised medals, types of datasets, models vs. datasets testing, and validation vs. verification testing. Based on these classifications, the paper then presented several testing scenarios of H0 and H1 along with the statistics used in each scenario. Future research will delve into the Python ML testing hypothesis. In the long run, conduct a systematic review of the literature to find out current and future challenges facing the ML testing hypothesis. |
KEYWORDS Machine learning, hypothesis testing, machine learning metrics |
|
Cite this paper Ghazi Alkhatib. (2024) Exploring Machine Learning Hypothesis Testing. International Journal of Computers, 9, 1-11 |
|
