Research on big data classification method based on improved KNN algorithm

K-nearest neighbor classification algorithm (KNN) is one of the simplest methods in data mining classification technology, it has been widely used in many fields because of its simplicity. However, when the sample size and the feature attributes are large, the classification efficiency of KNN algorithm will be significantly reduced. In this paper, an improved KNN algorithm based on k-value selection strategy is proposed. Two classification decision rules are added to the improved algorithm, which can effectively optimize the selection of k-value and the defects of classification decision rules. Through several groups of experimental tests, the results show that the improved classification algorithm can effectively improve the recognition rate of KNN classification algorithm.