I am dealing with a supervised anomaly detection problem, where I have labels with 0 for normal and 1 for abnormal. The default distribution of the dataset is highly imbalanced with a ratio of 96:4 for normal and abnormal respectively.

So, I applied random undersampling to decrease the ratio to 55:45 for normal and abnormal. Now, the accuracy is 95%. Is this concept correct, or am I wrong?