Attribute Noise, Classification Technique, and Classification Accuracy

Abstract

Binary data classification is an integral part in cyber-security, as most of the response variables follow a binary nature. The accuracy of data classification depends on various aspects. Though the data classification technique has a major impact on classification accuracy, the nature of the data also matters lot. One of the main concerns that can hinder the classification accuracy is the availability of noise. Therefore, both choosing the appropriate data classification technique and the identification of noise in the data are equally important. The aim of this study is bidirectional. At first, we aim to study the influence of noise on the accurate data classification. Secondly, we strive to improve the classification accuracy by handling the noise. To this end, we compare several classification techniques and propose a novel noise removal algorithm. Our study is based on the collected data about online credit-card transactions. According to the empirical outcomes, we find that the noise hinders the classification accuracy significantly. In addition, the results indicate that the accuracy of data classification depends on the quality of the data and the used classification technique. Out of the selected classification techniques, Random Forest performs better than its counterparts. Furthermore, experimental evidence suggests that the classification accuracy of noised data can be improved by the appropriate selection of the sizes of training and testing data samples. Our proposed simple noise-removal algorithm shows higher performance and the percentage of noise removal significantly depends on the selected bin size.