Early diagnosis of breast cancer is essential to save lives of patients. Usually, medical datasets include a large variety
of data that can lead to confusion during diagnosis. The Knowledge Discovery on Database (KDD) process helps to
improve efficiency. It requires elimination of inappropriate and repeated data from the dataset before final diagnosis.
This can be done using any of the feature selection algorithms available in data mining. Feature selection is considered
as a vital step to increase the classification accuracy. This paper proposes a Modified Bat Algorithm (MBA) for feature
selection to eliminate irrelevant features from an original dataset. The Bat algorithm was modified using simple random
sampling to select the random instances from the dataset. Ranking was with the global best features to recognize the
predominant features available in the dataset. The selected features are used to train a Random Forest (RF) classification
algorithm. The MBA feature selection algorithm enhanced the classification accuracy of RF in identifying the occurrence
of breast cancer. The Wisconsin Diagnosis Breast Cancer Dataset (WDBC) was used for estimating the performance
analysis of the proposed MBA feature selection algorithm. The proposed algorithm achieved better performance in
terms of Kappa statistic, Mathew’s Correlation Coefficient, Precision, F-measure, Recall, Mean Absolute Error (MAE),
Root Mean Square Error (RMSE), Relative Absolute Error (RAE) and Root Relative Squared Error (RRSE).