Fault prediction in software is an important aspect to be considered in software development because it ensures reliability and the quality of a software product. A high-quality software product consists of a few numbers of faults and failures. Software fault prediction (SFP) is crucial for the software quality assurance process as it examines the vulnerability of software products towards failures. Fault detection is a significant aspect of cost estimation in the initial stage, and hence, a fault predictor model is required to lower the expenses used during the development and maintenance phase. SFP is applied to identify the faulty modules of the software in order to complement the development as well as the testing process. Software metric based fault prediction reflects several aspects of the software. Several Machine Learning (ML) techniques have been implemented to eliminate faulty and unnecessary data from faulty modules. This chapter gives a brief introduction to SFP and includes a bibliometric analysis. The objective of the bibliometric analysis is to analyze research trends of ML techniques that are used for predicting software faults. This chapter uses the VOSviewer software and Biblioshiny tool to visually analyze 1623 papers fetched from the Scopus database for the past twenty years. It explores the distribution of publications over the years, top-rated publishers, contributing authors, funding agencies, cited papers and citations per paper. The collaboration of countries and cooccurrence analysis as well as over the year’s trend of author keywords are also explored. This chapter can be beneficial for young researchers to locate attractive and relevant research insights within SFP.