In the age of data, advanced analytics have been leveraged in the field of medical claim processing through the utilization of machine learning (ML) algorithms. The inclusion of machine learning algorithms within rule-based claims processing systems encounters challenges due to the diverse nature of healthcare policies and entities. Nevertheless, this research introduces innovative machine learning hybridization model designed for effective anomaly detection while processing large volumes of data. Intelligent Claim Edits using ML anomaly detection enhance the efficiency of claim process. The proposed hybrid ML model, Auto Learning Hybrid Model (ALHM), sequentially combines K-Means clustering model and One-Class Support Vector Machine model for identifying anomalies in claims by capturing heterogeneity in data and decomposing the population into smaller groups within the home healthcare services based on the wide range of services and associated reimbursements. The proposed hybrid model, ALHM, for detection of anomalies in home healthcare services achieved a precision of 98% and a recall of 97%. It has become imperative to ensure that the decisions and actions of the proposed hybrid model is understandable to healthcare program managers given the complexity of the machine learning technique. Hence an explainable ML model is achieved using visualizations developed for the outcomes generated by the proposed hybrid model, ALHM which is specifically tailored to the healthcare domain.