Applied Mathematics and Nonlinear Sciences
Journal license

Journal

Applied Mathematics and Nonlinear Sciences


Volume
& Issue

Volume 8, Issue 1


Published
on

April 28, 2023


Pages

1387-1400


DOI

Article

Analysis and elaboration of enterprise management innovation path based on logistic regression perspective


Authors

Jia Zhao Affiliation:
School of Tourism, Shanghai Normal University, Shanghai, 200234, China


Abstract

Based on the lack of management level and other problems in enterprise management innovation, this paper analyzes the innovation pathway of enterprise management by logistic regression algorithm. Firstly, the management pathway is set as a data set, and the feature vector of the model is defined, the probability model of logistic regression is derived from the input data vector, and the model defines the likelihood probability of the training set. Then the log-likelihood function of the logistic regression model with beta distribution is calculated, the feature weights of the data set are obtained using this function, and finally, the effective countermeasures of enterprise management innovation pathways under logistic regression are obtained according to these weights. The results show that by examining the variance comparison of different enterprise properties, private and sole proprietorship enterprises have the highest scores in the external organizational management factors, 3.86 and 3.72, respectively. The factors in the strategic technological capability have the lowest scores compared with other factors. It can be seen that the construction of comprehensive innovation management capability of enterprises is a long-term accumulation process, and the logistic regression algorithm helps enterprises to develop feasible innovation management pathway strategies according to their capabilities.


Keywords

Logistic regression algorithm, Dataset, feature weights, Beta distribution, Likelihood function, 62G08


Citation

Zhao, J. (2023). Analysis and elaboration of enterprise management innovation path based on logistic regression perspective. Applied Mathematics and Nonlinear Sciences, 8(1), 1387–1400. https://doi.org/10.2478/amns.2023.1.00042

Published by: Engineering Journals

Engineering Journals Logo