Manufacturing Big Data Modeling Based on KNN-LR Algorithm and Its Application in Product Design Business Domain

In product life cycle, it is very important to use the manufacturing big data to build prediction model and apply it to predict whether the design task of the product can be completed within the specified time. Most of the existing prediction models in manufacturing industry are built by a single algorithm or its improved version, and neglect the limitation of using a single forecasting algorithm, which may lead to poor forecasting accuracy. This paper aims to integrate the K-nearest neighbor classification algorithm and the logistic regression algorithm linearly in parallel to obtain the combined model which is called K-nearest neighbor-logistic regression (KNN-LR) in this paper, and use the combined model to predict whether the design task of the product can be completed within the specified time. Experimental results show that compared with the model built by a single algorithm, the combined model has better performance on model evaluation indicators such as accuracy, precision, F1 value. recall and classification error rate.