Start with the question
Choose problems where better evidence can change understanding or action.
Plotting the next route…
Plotting the next route…
curiosity → evidence → useful tools
About Akshay
I’m Akshay, a student researcher and builder interested in using data, artificial intelligence, and engineering to understand complex systems and create meaningful tools.
Why data science
My interests sit where computation meets the physical and human world: models, environmental measurements, interactive visualizations, research tools, and accessibility-focused technology.
I’m drawn to work that makes uncertainty visible, keeps its assumptions inspectable, and turns complex analysis into something people can actually use.
Research philosophy
Choose problems where better evidence can change understanding or action.
Document assumptions, preserve uncertainty, and show how a result was reached.
Treat accessibility, explanation, and real-world context as part of the technical work.
Current interests
Selecting a subject on the homepage reveals related projects. Here, the subjects form one research landscape rather than a list of percentages.
Sensing, measurement, air quality, and the behavior of physical systems.
Concentration, Chokepoints, and Supply-at-RiskModels that are evaluated carefully, interpreted honestly, and used responsibly.
World Cup Player ImpactPressure, Production, and NoiseConcentration, Chokepoints, and Supply-at-RiskAI literacy, fairness, and technology designed around real people.
Making quantitative reasoning more visible, intuitive, and useful.
Interfaces and tools that reduce friction and expand participation.
Turning complex evidence into clear, explorable visual stories.
World Cup Player ImpactPressure, Production, and NoiseConcentration, Chokepoints, and Supply-at-RiskContext, not a résumé dump
Start with a problem that matters, then identify the evidence needed to understand it.
Explore environmental sensing, artificial intelligence, statistical modeling, and human-centered technology as connected fields.
Use technical challenges and collaborative projects to sharpen reasoning, implementation, and communication.
Build clearer ways to move from raw data to an explanation that someone else can inspect and use.
Technical toolkit
Every tool links directly to the projects where it appears, keeping the map grounded in the work.
Tools used to express analyses and build reproducible systems.
Modeling, evaluation, interpretation, and responsible experimentation.
Turning analysis into legible, interactive evidence.
Collaboration interests