· 2019
Logistic Regression Model Optimization and Case Analysis
- 279citations
- 2019year
Short summary
Optimized logistic regression by improving the Sigmiod function and using gradient descent, reducing iterations and improving classification without sacrificing accuracy.
AI-generated from the title and abstract; the full text is not read.
Key points
- Logistic regression training is slow for large datasets.
- Sigmiod function was improved and gradient descent was used to find regression coefficients.
- The optimized model reduced the number of iterations.
- Classification effect improved with no significant change in accuracy.
AI-generated from the title and abstract; the full text is not read.
Abstract
Traditional logistic regression analysis is widely used in the binary classification problem, but it has many iterations and it takes a long time to train large amounts of data, which is not applicable. In this paper, we study the mathematical model of logistic, define the error function, find the regression coefficient by gradient descent method, and improve the Sigmiod function. Finally, the number of iterations is reduced, and the classification effect is better, and the accuracy is basically unchanged. Besides, this paper establishes a vehicle evaluation prediction model to predict whether consumers accept a certain car. It provides a certain reference for the binary classification problem.
The authors' abstract, as published at the source., 2019 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Business and International Management
Business and International ManagementBusiness, Management and Accounting