Quality Assurance Challenges For Machine Learning Software Applications During Software Development Life Cycle Phases

@article{Alamin2021QualityAC,
  title={Quality Assurance Challenges For Machine Learning Software Applications During Software Development Life Cycle Phases},
  author={Md. Abdullah Al Alamin and Gias Uddin},
  journal={2021 IEEE International Conference on Autonomous Systems (ICAS)},
  year={2021},
  pages={1-5}
}
In the past decades, the revolutionary advances of Machine Learning (ML) have shown a rapid adoption of ML models into software systems of diverse types. Such Machine Learning Software Applications (MLSAs) are gaining importance in our daily lives. As such, the Quality Assurance (QA) of MLSAs is of paramount importance. Several research efforts are dedicated to determining the specific challenges we can face while adopting ML models into software systems. However, we are aware of no research… 

Figures from this paper

"Project smells"-- Experiences in Analysing the Software Quality of ML Projects with mllint
TLDR
This research evaluates the novel concept of project smells which consider deficits in project management as a more holistic perspective on software quality in ML projects in the industrial context of ING, a global bank and large software- and data-intensive organisation.

References

SHOWING 1-10 OF 43 REFERENCES
Software Engineering for Machine Learning: A Case Study
  • Saleema AmershiA. Begel T. Zimmermann
  • Computer Science
    2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP)
  • 2019
TLDR
A study conducted on observing software teams at Microsoft as they develop AI-based applications finds that various Microsoft teams have united this workflow into preexisting, well-evolved, Agile-like software engineering processes, providing insights about several essential engineering challenges that organizations may face in creating large-scale AI solutions for the marketplace.
Machine Learning for Software Engineering: A Systematic Mapping
TLDR
A systematic mapping study on applications of machine learning to software engineering following the standard guidelines and principles of empirical software engineering introduces a machine learning for software engineering (MLSE) taxonomy classifying the state-of-the-art machine learning techniques according to their applicability to various software engineering life cycle stages.
Requirements Engineering for Machine Learning: Perspectives from Data Scientists
TLDR
It is concluded that development of ML systems demands requirements engineers to understand ML performance measures to state good functional requirements, be aware of new quality requirements such as explainability, freedom from discrimination, or specific legal requirements, and integrate ML specifics in the RE process.
Software Engineering Challenges of Deep Learning
TLDR
The challenges identified in this paper can be used to guide future research by the software engineering and DL communities and could enable a large number of companies to start taking advantage of the high potential of the DL technology.
How does Machine Learning Change Software Development Practices?
TLDR
This study uncovers significant differences in various aspects of software engineering and work features between the development of machine learning systems and theDevelopment of non-machine-learning systems.
Challenges in Deploying Machine Learning: a Survey of Case Studies
TLDR
By mapping found challenges to the steps of the machine learning deployment workflow it is shown that practitioners face issues at each stage of the deployment process.
Quality Assurance for AI-Based Systems: Overview and Challenges (Introduction to Interactive Session)
TLDR
This paper defines basic concepts and characterize AI-based systems along the three dimensions of artifact type, process, and quality characteristics and outlines the key challenges of understandability and interpretability of AI models.
Machine Learning Testing: Survey, Landscapes and Horizons
TLDR
This paper provides a comprehensive survey of techniques for testing machine learning systems; Machine Learning Testing (ML testing) research, covering 144 papers on testing properties, testing components, and application scenarios.
Engineering Reliable Deep Learning Systems
TLDR
The current perspective of relevant AI engineering concepts and some key challenges that need to be overcome to make significant progress in this important area are presented.
Ways of Applying Artificial Intelligence in Software Engineering
  • R. FeldtF. G. O. NetoR. Torkar
  • Computer Science
    2018 IEEE/ACM 6th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering (RAISE)
  • 2018
TLDR
The AI in SE Application Levels (AI-SEAL) taxonomy is presented that categorises applications according to their point of application, the type of AI technology used and the automation level allowed and shows the usefulness of this taxonomy by classifying 15 papers from previous editions of the RAISE workshop.
...
...