Food adulteration is the problem most general in the food industry and affects quality and safety of consumables taken by masses. Honey is one of the treasured natural resources and is very often adulterated by mixing cheaper materials like sugar syrups that cause grave concern on health and confidence of consumers. The paper provides a cross-cutting approach at the detection of honey adulteration by using two of the most complex advanced ML techniques: GBM and RL. We shall attempt to design the model not only to detect adulteration in the honey but predict at which price the honey could be sold in the market. The inclusion of RL enables the model to adaptively optimize the learning process to present high accuracy and efficiency. With the goal of improving food safety with a real-time detection system that is both economy-scale and cost-effective, this project can be used effectively by either producers or regulators or consumers.