Taiwan’s auditors have suffered from processing excessive audit data, including drawing audit evidence. This study advances sampling techniques by integrating machine learning with sampling. This machine learning integration helps avoid sampling bias, keep randomness and variability, and target the risker samples. We first apply a Naive Bayes classifier to classify data into some classes. Next, a user-based, item-based, or hybrid approach is employed to draw audit evidence. The representativeness index is the primary metric for measuring the representativeness of audit evidence. The user-based approach denotes the selection of samples between two percentiles in a class as audit evidence. It may be equivalent to a combination of monetary and variable sampling methods. The item-based approach represents the choice of risky samples as audit evidence. It may be identical to a combination of non-statistical and monetary sampling methods. Auditors can hybridize those user-based and item-based approaches to balance representativeness and riskiness in selecting audit evidence. Three experiments show that sampling using machine learning integration has the benefits of drawing unbiased samples, handling complex patterns, correlations, and unstructured data, and improving efficiency in sampling big data. However, the limitations are the classification accuracy output by machine learning algorithms and the range of prior probabilities.