A company has a history of access logs stored in an Amazon S3 bucket. The company’s data engineer filtered out the dataset to only contain pairs of (user/IP) where it contains the name of the IAM user along with the IP address used to access a specific service. The machine learning engineer is tasked with creating a model which takes an input of (users/ID) pairs and outputs a score. A threshold is to be set such that a score higher than this threshold should be flagged as anomalous. Which algorithm should be used to train such model and what is the type of this machine learning problem?