Postpartum depression is a medical condition which continue to affect many mothers after delivery even though the disease can be prevented. It consequently exposes mothers and family members to illness and even death. Families, governments and other stakeholders incur heavy expenditure in the management of the disease. Research studies have been done to develop machine learning models for prediction of mothers at risk of postpartum depression during pregnancy for preventive measures. This paper presents a literature review of the machine learning prediction models which have been developed for the condition with specific focus on feature selection methods, algorithms used and the resulting performance. Literature review was done with google scholar integrated to an online institutional account for e-resources from e-databases accessed by subscription or free access. Inclusion involved all articles with the key words “machine learning, prediction model, postpartum depression” in the articles dated from 2018 to 2022 and sorted by relevance. A total of 3430 articles were listed while only 17 which were accessible with full text were eligible and therefore selected for the study. Analyzes were done using Microsoft Excel and descriptive analysis. Findings and conclusions will inform scientists on the status of research in the area to guide new studies, and inform the market on the potential benefits of integrating machine learning models in their systems.