Due to the advancement in technology as well as the availability of standardized image editing tools, image forgery is on the rise among many other concerns that are believed to be unique to the digital age. Manipulations of images result in loss of the true nature and quality of the image and present various difficulties in several fields such as digital forensics, media, and law enforcement systems. There is a need for identification of existing effective image forgery detection methodologies for checking authenticity of images. The objective of this research is to develop a holistic data analytical model that uses sophisticated approaches, like machine learning and statistical methods to identify and solve the problems of disparity in images. ELA and PRNU alongside other techniques and deep learning algorithms are ideas used in the developed model to improve detection accuracy as a solution to forged images. Finally, the use of ‘machine learning’ provides the model with the flexibility of enhancing the identification of newer faked documents. Thus, employing these various approaches, the framework’s purpose is to provide a flexible and effective solution to adapt to new challenges of image forgery. Data analytics framework helps to act on big amounts of image data as fast as possible. Thus, with the help of big data techniques, the given framework gives the possibility to analyze large amount of data in order to distinguish patterns that may potentially represent forgery.