This paper takes a case study approach towards employing Machine Learning to extract pertinent data from the tabular document. Firstly, this paper focuses on two main areas: it explores the tools available in the market as out-of-box products utilized as self-service tools to cleanse the data files in the expected format. Secondly, it conducts a thorough analysis using machine learning algorithms to hypothesize that users can leverage machine learning for data pre-processing successfully.