The paper evaluates the effectiveness of decision tables as a hypothesis space for supervised learning algorithms. Decision tables, being one of the simplest hypothesis spaces, are easy to understand and often perform well on both artificial and real-world datasets with discrete features. The IDTM (Inducer of DTMs) algorithm, which induces decision tables, sometimes outperforms state-of-the-art algorithms like C4.5, even on datasets with continuous features. The performance of IDTM is surprisingly good on some datasets with continuous features, indicating that these features may not be utilized effectively by C4.5 or that they have few values. The paper also introduces an incremental method for cross-validation, which is applicable to incremental learning algorithms like IDTM. This method allows for efficient cross-validation in time linear in the number of instances, features, and label values, making it suitable for real-time applications. The paper concludes by discussing the strengths and limitations of decision tables and their potential for future research.The paper evaluates the effectiveness of decision tables as a hypothesis space for supervised learning algorithms. Decision tables, being one of the simplest hypothesis spaces, are easy to understand and often perform well on both artificial and real-world datasets with discrete features. The IDTM (Inducer of DTMs) algorithm, which induces decision tables, sometimes outperforms state-of-the-art algorithms like C4.5, even on datasets with continuous features. The performance of IDTM is surprisingly good on some datasets with continuous features, indicating that these features may not be utilized effectively by C4.5 or that they have few values. The paper also introduces an incremental method for cross-validation, which is applicable to incremental learning algorithms like IDTM. This method allows for efficient cross-validation in time linear in the number of instances, features, and label values, making it suitable for real-time applications. The paper concludes by discussing the strengths and limitations of decision tables and their potential for future research.