Presentation on Explainable Software Analytics for MITS5002

This presentation analyzes the paper "Explainable Software Analytics" by H.K., Dam, T. Tran, and A. Ghose, focusing on its evaluation of software analytics and the application of artificial neural networks. The presentation covers the paper's intention, research methods (including qualitative design and inductive approach), data collection, and analysis techniques. It highlights the issues addressed, such as the need for explainability in software analytics, and presents the results and findings, emphasizing the benefits of explainable software analytics for risk prediction. The presentation concludes that the implementation of artificial intelligence-based software analytic models can help companies address risks and enhance prediction effectiveness. The paper examines the significance of software analytic models, the characteristics of explainable software analytics, and the adoption of secondary methods. The presentation emphasizes the importance of software analytics for the business communities for achieving larger prediction effectiveness.

Explainable Sofware
Analytics
H.K., Dam, T. Tran and, A., Ghose, “Explainable software
analytics,” In Proceedings of the 40th International Conference on
Software Engineering: New Ideas and Emerging Results, vol. 12,
no. 6, pp. 53-56, 2018.

 The major identification of the investigation
is to evaluate the software analytics and
review an article based on artificial neural
networks.
 The chosen paper is “Explainable Software
Analytics” which was presented by Hoa,
Truyen and Aditya in the year 2018 [1].
 This presentation will cover intention of
paper, research methods, issues included,
results and findings.
Introduction

 The authors found that software analytics is
a key topic for the research as companies
are moving towards such models and
systems.
 Software analytics models are based on
machine learning and AI programs that
help to defect prediction [2].
 Research question: How might companies
evaluate explainability of software analytics
frameworks?
Intention and content of the
paper

 The intention of the paper is to evaluate the
significance of software analytic models.
 This paper provided depth information
about software analytics that can help to
enhance skills.
 The writers examined the key
characteristics of explainable software
analytics.
Intention and content of
paper

 There are numerous research
methodologies are adopted in the paper
including
◦ Research design
◦ Research approach
◦ Data collection
◦ Data analysis
Research methods

 The qualitative design is adopted by writers
due to its ability to provide effective
information and manage the research gaps
easily.
 Using such design the writers implemented
effective plans and strategies in the
investigations by which the developed
research questions are addressed
effectively [3].
Research design

 In which, an inductive approach is added
due to the subjective nature of the topic.
 It helped the writers to perform in-depth
analysis in regards to the software analytic
models.
 Such approach managed the research gaps
and helped to achieve the developed aims
and goals effectively [4].
Research approach

 In the chosen paper the secondary methods are
adopted that helped to include the theoretical
information in the investigation in regards to
the software analytics.
 A literature review is conducted that evaluated
the findings of recent papers about software
analytics and reduced the research gaps
effectively.
 Numerous sources are included in the data
gathering techniques including peer-reviewed
papers, online websites, books and many more.
Data collection methods

 The writers adopted a content analysis that
has the ability to provide effective
information and analyze the data easily.
 The presence of such methods can manage
the research gaps and address the research
concerns in an appropriate manner.
 Such methods provided reliable and
appropriate techniques to the investigators
and completed the research effectively.
Data analysis

 The investigators addressed and highlighted
the problems of risk predictions from the
computing software
 Using explainable software analytics the
companies can solve complex tasks easily
and defect the predictions and risks in an
appropriate manner.
Issues highlighted

 It is found that software analytics are reluctant
to trust predictions developed by the analytics
machinery without understanding the rationale
for those predictions.
 The writers believed that making predictive
models can help companies to achieve
accurate and effective predictions.
 Explainability must be a significant measure for
evaluating software analytic models or
frameworks and can be utilized for analyzing
larger datasets easily.
Results and findings

 The implementation of a software analytic
model is beneficial for the companies by which
the effectiveness of risk prediction can be
enhanced.
 The writers found that explainable software
analytics can be used to facilitate individual
understanding of machine prediction.
 The chosen paper is linked to the unit of
assignment where the writers highlighted
points about software analytics that helped to
enhance skills of the readers.
Conclusions of the paper