This document introduces Hivemall, an open-source machine learning library built as a collection of Hive user-defined functions (UDFs). Hivemall allows users to perform scalable machine learning on large datasets stored in Hive/Hadoop. It supports various classification, regression, recommendation, and feature engineering algorithms. Some key algorithms include logistic regression, matrix factorization, random forests, and anomaly detection. Hivemall is designed to perform machine learning efficiently by avoiding intermediate data reads/writes to HDFS. It has been used in industry for applications such as click-through rate prediction, churn detection, and product recommendation.