This paper is published in Volume-5, Issue-2, 2019
Area
Machine Learning
Author
Sudipto Nandan
Org/Univ
Oracle India Private Limited, Bengaluru, Karnataka, India
Pub. Date
25 March, 2019
Paper ID
V5I2-1418
Publisher
Keywords
Anomaly detection, Regression results, Isolation forest, Principal Component Analysis

Citationsacebook

IEEE
Sudipto Nandan. Anomaly detection in code base, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Sudipto Nandan (2019). Anomaly detection in code base. International Journal of Advance Research, Ideas and Innovations in Technology, 5(2) www.IJARIIT.com.

MLA
Sudipto Nandan. "Anomaly detection in code base." International Journal of Advance Research, Ideas and Innovations in Technology 5.2 (2019). www.IJARIIT.com.

Abstract

Any product when under development, goes through numerous changes before finally being released to the customer. While these changes are being done, it adds new features, modifies existing ones. How do we know if a product is in good shape to be released? Yes, we test the product, run the existing unit, functional, performance tests etc. What if the number of tests is in 10000s. How do we analyse each test result? Is there an automated way to detect the overall health of the product using the results of regression tests? Anomaly Detection using machine learning algorithms gives us a way to find out the overall health of the product. Using Anomaly Detection, we can quickly find out about the code base and if new changes should be allowed in before the existing code base is stabilized. It helps to determine, how far the existing code base is away from being released to the customer. It can help the code base to be almost always stable irrespective of the number of code changes that are merged into it.
Paper PDF