Pharmaceutical or consumer product shelf-life for any new variant is subject to its Active Pharmaceutical Ingredients (API) and various environmental / storage conditions like temperature, humidity, and packaging material. Any of these factors can change the chemical stability of a drug or a consumer product. As a result, long-term testing and accelerated testing need to be conducted to determine the shelf life of the new product or a new variant. This paper presents factors that can affect a product and shows how Machine Learning (ML) can be adapted to predict changes to the API. Thus, any change to the new product or variant can be studied with the help of ML analytics and can act as a tool based on the historical LIMS database. Stability analytics aims to build a ML model which can predict the stability value of the components and how they react in contrast conditions.