Experiments have traditionally played a vital role in the discovery and characterization of novel materials. Experimental research must be carried out over a lengthy period of time for a small number of materials, as it necessitates a lot of resources and equipment. Due to these constraints, significant discoveries were made primarily by human intuition or serendipity. Metals, semiconductors, ceramics, and polymers are the most common types of materials. Nanomaterials, biomaterials, and energy materials, to name a few, are among the new and sophisticated materials being produced. Machine learning is one of the most interesting new methods to enter the material science toolkit in recent years. This set of statistical tools has already demonstrated its ability to significantly accelerate both fundamental and practical research. At present, there is a plethora of effort being made to create and apply machine learning to solid-state systems.