Machine’s ability to display human-like capabilities such as reasoning, learning, planning and creativity has taken Artificial Intelligence (AI) to the next level. AI enables technical systems to efficiently perceive their environment, solve problems and act to achieve a specific goal. A Large Language Model (LLM) is another subfield of AI that uses deep learning techniques and massively large data sets to understand, summarize, generate and predict new content. LLMs are trained on a huge volume of datasets and it makes them quite suitable for e-Discovery tasks. This paper covers the efficacy of LLM like ChatGPT for the Corporate fraud investigation based on e-Discovery technique. A case study is also covered to ascertain whether e-Discovery technique yields relevant scientific-evidence as per the forensic procedures for corporate frauds. An LLM based e-Discovery approach for forensic analysis on two major corporate frauds of similar nature was performed to draw forensic inferences. The outcome of such analysis is useful for investigating the corporate fraud and cold-cases of the similar nature by the forensic experts.