#ATAGTR2023 Speaker

Welcome to the 8th Edition of the Global Testing Retreat 2023!

About Speaker

Aishvarya is a seasoned performance test engineer with 11 years of experience in performance testing. She is a key member of innovation team in NFT practice and has played a key role in developing several patented innovative solutions for industry problems using java/python and ELK stack.
She loves coming up with creative solutions leveraging latest technologies to solve business challenges.

Srithanga Aishvarya T

Performance Test Manager at Cognizant

Interactive Talk -  Machine Learning Model to automate performance test script development using JMeter

Machine Learning Model to automate performance test script development using JMeter


This abstract outlines the potential and benefits of implementing a Machine Learning (ML) model to automate Performance test script development activities using JMeter as the load testing tool.



We propose the construction of a Supervised Machine Learning model to automate script enhancement in JMeter. The model will receive the recorded JMeter script and JTL file as inputs and consist of the following components:

  • Autocorrelation
  • Standardization
  • Run and Debug
  • Alerts & Reporting
  • Reuse


Autocorrelation: This component identifies left, right boundaries, and match counts for correlation. Leveraging training data knowledge, it identifies parameters for correlation and customizes the script accordingly.


Standardization: This module ensures uniform application of text checks across scripts, with users having the flexibility to review, modify, or eliminate standardizations.


Run and Debug: Integrating ML with scripting practices, the engine modifies the JMX script to include necessary customizations for a tailored JMeter test plan. The ML model executes tests via command-line execution.


Alerts & Reporting: These elements inform users of the need for manual intervention and provide comparisons between new and previous release scripts.


Reuse: This component streamlines script development by enhancing new scripts using reference scripts from previous releases of the same application.


Training the Model: The model’s effectiveness stems from a blend of protocol, technology, and domain-level insights. This amalgamation enables the model to discern correlations and customizations critical to script development. By utilizing JMeter’s open-source ecosystem, the approach seamlessly integrates existing plugins and libraries.


Benefits: Script development, especially with open-source tools like JMeter lacking autocorrelation features, is resource-intensive. As open-source usage increases and JMeter remains a preferred tool, this ML model reduces manual efforts, significantly enhancing cost savings without compromising quality.


Further Enhancements: We suggest exploring the integration of this model with Language Models (LLMs) to enhance web UI automation as an additional feature.


In conclusion, combining JMeter’s scripting capabilities with ML techniques provides a streamlined approach to performance testing. This integration is particularly valuable within the open-source landscape. With JMeter’s continued prominence, the integration of Python, ML, and JMeter empowers professionals and elevates performance testing. This transition translates into substantial cost savings while maintaining quality, highlighting the symbiotic relationship between technological innovation and performance optimization.

Hear what Aishvarya has to say about the interactive session
Scroll to Top