Aadi_Portfolio

Aaditya Bhatia

Software researcher and a data-geek.

I am currently pursuing my Ph.D. at Software Analytics and Intelligence Lab, under the supervision of Prof. Ahmed E Hassan, Queen's University.
As a part of my research, I use statistics, machine learning, and NLP techniques for data analysis. I research software engineering domains like software ecosystems, developer-corwdsourcing, bug management systems, and software code quality.
I enjoy being the investigative journalist, uncovering data-intrinsic patterns and connecting the dots towards a higher level of domain intelligence.

What I’m good at?

Data Science

Building and productionizing predictive models on large scale datasets by using statistical modelling, machine learning and other data analytics approaches.

Data Analytics

Interpreting and analyzing data to uncover data-intrinsic insights. Converting data into insights, and insights into domain-knowledge by formulating actionable strategies.

Leadership

Driving R&D projects through effective leadership skills, combining research skills with ability to motivate and collaborate with the team. Detail-oriented and efficient, with strengths in both software-project and time management. Ability to plan and execute projects and tasks with the perfect blend of research, software development, team communication, and enjoyment.

Research

Strong research skills attested by two publications in top-tier journals and a US-grant patent. My publications are in effective designing of issue management systems. I use statistical analysis, machine learning tools, natural language processing for performing my research. My patent is on a hybrid-reality-based robot.

Publications and Patent

Publications

"A Study Of Bug Management Using Stack Exchange Q&A Platform", TSE 2020. (Published)

"A Study Of Differences Between Bugs And Features Using Stack Exchange Q&A Platform", TSE. (In review)

Traditional issue management systems like Bugzilla are widely used in open source and commercial projects. My research focusses on using effective crowdsourcing management beahviors in better management and performing operations of issue management systems. I researched Stack Exchange, that uses its online question and answer (Q&A) platform to manage bugs. This brings several new unique features that are not offered in traditional bug management systems.
For my first journal, I researched the unique features of Stack Exchange Q&A platform that allow users to directly edit a bug report (i.e., the in-place editing feature) instead of commenting about the bug report; use different communication channels (i.e., the answering and commenting features) to discuss reported bugs, and vote on those bug reports, answers, and their associated comments (i.e., the voting feature). Along with my collaborators, I proved how these unique features are used to manage bugs, and provide insights to the designers of traditional bug management systems who are considering introducing such features in their bug management system.

For my second journal paper, I performed a study of the differences between bug reports and feature requests in the Stack Exchange issue management system. This research was performed because: 1) Stack Exchange contains a large number of issues that have been carefully tagged as bug reports versus feature requests. 2) the issue management was carried out through a Q&A platform, which provides us with a richer perspective on the differences between the management of bug reports and feature requests. I found that bug reports and feature requests differ significantly from each other along many dimensions such as the amount of community participation, the content of the issues, and the characteristics of the participating users. I built classification models for automated identification of bug reports from feature requests with a median AUC of 0.90. The developers of issue management systems and software practitioners can leverage such understanding to improve issue management processes in large software projects.

Patent: Hybrid reality based robotic navigation and control

Semi-autonomous robots are used in industry as well as scientific missions like mars rover. I built a land-robot similar to the mars-rover design. The interaction, navigation and control over the semi-autonomous robot was based on the movement triggered by a virtual reality device. Moving the VR-headset controlled motion of the robot. The robot can interact with people in real time and can also identify if the robot had already interacted with person. The US-grant patent is provided to my ex-company, Tata Consultancy Services, with me as a team member.

Featured Software Projects

For a detailed list of my projects, please check my Github link. Feel free to fork my industrial projects for your company. Contact me if you would like to contribute / codevelop on any of my projects.