PHD RESEARCHER · UNIVERSITY OF CENTRAL FLORIDA

Reliable AI.
Fairer decisions.

Mayra Bornacelly Castaneda

I study how neural decision systems behave when the data changes, and what that means for reliability and fairness.

Distribution shiftAI reliabilityAlgorithmic fairness
RESEARCH LENSDATA / SHIFT
Data, boundaries, and changing conditionsAn illustrative scatterplot with two groups of points and a curved decision boundary. Move the slider below to shift the points. It is a conceptual illustration, not a research result. REPRESENTATION SPACE Decision boundary
Group AGroup B
Original distributionShifted distribution

Conceptual illustration, not experimental results.

At the intersection of

Machine learningIndustrial engineeringHuman factors

01 / RESEARCH

Looking beyond
prediction alone.

My work examines model vulnerability and subgroup error patterns through gradients, learned representations, and decision-boundary geometry.

I connect these diagnostics with risk-aware human–AI decision support. Three complementary lines of research shape that work.

01

SciMargin

In press · ICAI 2026

Where do decision boundaries expose groups to error?

Class-conditioned boundary-exposure diagnostics for studying fairness degradation under distribution shift. Evaluated on Adult, COMPAS, and German Credit.

02

Basal Stability γ

In press · ANNSIM 2026

What can gradients reveal after a model has converged?

A co-developed, supervised diagnostic of post-convergence optimization pressure, measured with model parameters held fixed, to study reliability under changing data conditions.

03

FairTube

Working manuscript

Can a shared perturbation explain different group errors?

A geometric and finite-sample framework for testing whether a specified perturbation in representation space can jointly explain group-specific error patterns.

METHODS & TOOLS

PyTorch · Automatic differentiation · GPU experimentation · Representation analysis · Subgroup error analysis

02 / SCHOLARSHIP

Research in print & progress.

Published work, accepted manuscripts,
and conference contributions.

10 contributions

Statuses reflect the November 2026 CV. In-press work and accepted presentations are listed separately from published articles.

03 / TEACHING & COMMUNITY

Making knowledge
useful to others.

IN THE CLASSROOM

Probability and Statistics
for Engineers

STA 3032 · University of Central Florida

As an Instructor of Record and Graduate Teaching Associate, I develop assessments, instructional materials, and applied course projects.

May 2026–present · Previously Graduate Teaching Assistant, August 2025–May 2026

UPCOMING · SPRING 2027

In person

Honors Probability and Statistics for Engineers

STA 3032H · Section 0202 · University of Central Florida

Scheduled instructor for the in-person honors section in Spring 2027.

MENTORSHIP & LEADERSHIP

Supporting the next step.

INFORMS Mentor Match mentor, with a focus on machine learning, undergraduate research, and preparation for summer opportunities.

Graduate Advisor to the IEOM Student Chapter at UCF, supporting recruitment, faculty coordination, and academic and professional activities.

Previously: In2science science mentor, University of Melbourne.

SELECTED ACADEMIC SERVICE

  • NeurIPS 2026Ethics Reviewer
  • INFORMS WDS 2026Program Committee
  • AIAS+ 2026Program Committee & Reviewer
  • SN Computer ScienceReviewer · 2026

SUMMER 2026 / STUDENT FEEDBACK

Student Perception
of Instruction

4.72/ 5

Course & Content

4.61/ 5

Instructor & Instruction

Source: UCF Summer 2026 SPI report. These are separate category scores, not a combined overall rating.

SELECTED INVITED CONTRIBUTIONS

Ideas in conversation.

  • 2026
    AI Panel · 3rd IEOM World Congress

    Advanced Manufacturing and Industrial AI Innovation · Irvine, USA

    Panelist
  • 2026
    AI-Powered Engineering

    Redefining Problem Solving in the Digital Era · IEOM North America, Milwaukee

    Panelist
  • 2025
    Unlocking Research Impact: From Idea to Publication

    Southern Arkansas University

    Keynote

04 / ACADEMIC PROFILE

A perspective built
across disciplines.

Download CV (PDF) November 2026 CV · 3 pages

My path brings together computer science, engineering management, economics, and data science, alongside professional experience in data and IT operations.

EXPECTED 2029

Ph.D. in Industrial Engineering

University of Central Florida · USA

Cumulative GPA: 4.00 / 4.00

M.Sc. in Data Science

University of Melbourne · Australia

Graduate Diploma in Economics

Pontificia Universidad Javeriana · Colombia

Graduated with honors

M.S. in Engineering Management

Universidad de La Sabana · Colombia

Research-based degree

B.S. in Computer Science

Universidad San Martín · Colombia

Graduated with honors

05 / LET’S CONNECT

Building more
trustworthy systems.

I’m interested in US research fellowships and academic collaborations focused on reliable, fair, and risk-aware machine learning.

Find me on ORCID

Mayra Bornacelly Castaneda

PhD Researcher · Industrial Engineering
University of Central Florida
Research fellowshipsAcademic collaborationScholarly exchange