Cecilia Ferrando

Research Assistant in Machine Learning and Artificial Intelligence

University of Massachusetts, Amherst

I am a second-year PhD student in the College of Information and Computer Sciences (CICS) at the University of Massachusetts, Amherst. My current research is on statistical inference under differential privacy. I'm broadly interested in statistical machine learning and privacy-preserving machine learning. I am fortunate to be advised by professor Daniel Sheldon.

Before starting my PhD, I obtained a MS in Computational Design at Carnegie Mellon University, where I was supported by the Fulbright Scholarship. Upon graduating from Carnegie Mellon, I worked as a Machine Learning Software Engineer at Cadence, Pittsburgh.

Besides research and courses, I serve as Co-Chair of the PhD Applicant Support Program. I'm also co-leading the organizing committe of Voices of Data Science at UMass Amherst 2021.


  • Statistical machine learning
  • Privacy guarantees in machine learning
  • Artificial intelligence


  • PhD in Computer Science, 2024

    University of Massachusetts, Amherst

  • MS in Computational Design, focus on Machine Learning, 2018

    Carnegie Mellon University

  • BA+MA in Economics and Statistics, 2016

    Collegio Carlo Alberto

  • BSc+MSc in Architecture, 2015

    Politecnico di Torino




Machine Learning

Deep Learning


Data Analysis

Differential Privacy

Probabilistic Graphical Models

Reinforcement Learning



Research Assistant

College of Information and Computer Sciences, University of Massachusetts, Amherst

Sep 2019 – Present Amherst, MA
Machine Learning research with prof. Daniel Sheldon

Machine Learning Software Engineer

Cadence Design Systems

Jun 2018 – May 2019 Pittsburgh, PA
Applied research in deep learning, GANs and unsupervised learning

Quantitative Research Intern

Procore Technologies

May 2017 – Jul 2017 Santa Barbara, CA
Statistical data analysis for UX

Research Assistant

CodeLab, Carnegie Mellon University

Apr 2017 – Sep 2017 Pittsburgh, PA
Computational design research with prof. Daniel Cardoso Llach


Quickly discover relevant content by filtering publications.

General-Purpose Differentially-Private Confidence Intervals

One of the most common statistical goals is to estimate a population parameter and quantify uncertainty by constructing a confidence …

Architectural Distant Reading Using Machine Learning to Identify Typological Traits Across Multiple Buildings

This paper introduces an approach to architectural “distant reading”: the use of computational methods to analyze architectural data in …

A Machine Learning Framework for Spatial Analysis

Can Machine Learning algorithms become a useful tool in the analysis of architectural space? Motivated by this question, in this poster …