<p><span>Diabetes is a fast spreading illness, which makes to worry millions of people around the globe. The people affected by type-2 diabetes are rapidly increasing and there are no effective diagnostic systems to control the diabetics. As per global health statistics, in western countries, population effected by type 2 diabetics are higher in rate and cost factor for treatment is increasing. There are no effective methods to eradicate the diabetes and it leads to carry out an investigative study on this disease. In existing reviews, researchers are using data analysis approaches to link the cause for diabetes with the patients based on the diet, life style, inheritance details, age factor, medical history, etc. to identify the root cause of the problem. By having multiple key factors and historical datasets, there are some data mining tools were developed, to generate new rules on the root cause of the disease and discover new knowledge from the past data’s, but the accuracy was not promising. The main objective of this paper is to carry out a detail literature review and design a conceptual data mining method at initial stage and implement it to improve the result accuracy compared to other classifiers. <br /> In this research, two data-mining algorithm were proposed at conceptual level: Self Organizing Map (SOM) and Random Forest Algorithm, which is applied on adult population datasets. The data set used for this research are from UCI machine Learning Repository: Diabetes Dataset. In this paper, <br /> data mining algorithms were discussed and implementation results were evaluated. Based on the result performance evaluation, Self-organizing maps have performed better compared to the Random Forest and other data mining algorithms such as naïve Bayes, decision tree, SVM and MLP for diagnosing the diabetes with better accuracy. In future, once system is implemented, <br /> it can be integrated with diabetic detector device for faster diagnosis of TYPE 2 diabetes disease.</span></p>