Data Selection and Machine Learning Algorithm Application Under the Background of Big Data

Abstract

At present, machine learning, as an important tool in data mining, is not only the exploration of human cognitive learning process, but also the analysis and processing of data. Facing the challenge of large amounts of data, part of the current research focuses on the improvement and development of machine learning algorithms, and another part of the researchers is devoted to the selection of sample data and the reduction of data sets. These two aspects of research work are parallel. Training sample data selection is a research hotspot in machine learning. Through effective selection of sample data, more informative samples are extracted, redundant samples and noise data are eliminated, so as to improve the quality of training samples and obtain better learning performance. This article aims to study data selection and the application of machine learning algorithms in the context of big data. Based on the analysis of machine learning implementation methods, the construction process of random forests, and random group sampling integration algorithms, the application of random group sampling methods is used to accurately select bases. Compared with the previous algorithms, the RPSE algorithm greatly improves the calculation speed of the data in the classifier and training samples, and ensures that the base classifier performs random calculations on the samples during training. According to the integrated gap spacing, a support vector machine training data can be selected, and the selected data set that needs to be filtered is used as a classifier for the support vector machine for training, so as to obtain the final classification. The experimental results show that compared with the more common traditional data selection algorithms, the RPSE algorithm greatly accelerates the accuracy and speed of data selection, and reduces the accuracy and precision of the support vector computer classification under the necessary conditions.