Type II diabetes is the deadliest disease. It must be identified early to be cured. Prediction models for detection systems typically use common parameters that might not be suitable for all individuals with various health conditions. As a result, this study suggests a way for diabetes type II prediction using variables that reflect individual health issues. More specifically, this work proposes a unique prediction method called Average Weighted Objective Distance (AWOD) based on the idea that the person has a variety of health states coming from a variety of individual characteristics, which is a need for an efficient prediction model. Using information gain to expose significant and inconsequential individual components with varying priorities, denoted by distinct weights (AWOD), modifies Weighted Objective Distance (WOD). To calculate AWOD, the data set is split into a training set and a testing set. The training set is utilized to establish all significant thresholds and constant values. In particular, binary classification issues with a small dataset are developed by AWOD. Two open-source datasets, Pima Indians Diabetes (First Dataset) and Mendeley Data for Diabetes (Second dataset) are examined to validate the suggested methodology. With machine learning-based prediction techniques like (K-Nearest Neighbors, Support Vector Machines, and Random Forest), the prediction performance for both datasets is compared, including statistical measures: Accuracy, Sensitivity, and specificity. The AUC-ROC curve graph reveals how well the model can differentiate across classes for all ML classifiers. The comparison findings demonstrated that the ML classifiers resulted in poor accuracy for the first Dataset. Although better for the second Dataset, the proposed method had greater accuracy than other machine learning based methods, with 95.26 percent and 99.01 percent for Datasets I and II, respectively.