Anna Dai

Data Scientist | Machine Learning & Data Systems

trivago

Biography

Anna Dai is a Data Scientist at trivago working on large-scale machine learning and data systems for travel search and pricing analytics.Her work focuses on scalable data pipelines, applied machine learning, and improving production systems that support decision-making across millions of travel searches.

Previously, she conducted research in natural language processing at the EPFL NLP Lab under Professor Antoine Bosselut, where her work explored responsible and secure machine learning systems. She holds an MSc in Data Science from Duke University. Anna is particularly interested in applied machine learning research that bridges academic ideas and real-world systems, especially in areas such as large-scale modeling, efficient data processing, and responsible AI.

Interests

Large-scale Data Systems
Natural Language Processing
Applied Machine Learning
Responsible AI

Education

MSc in Data Science, 2023
Duke University, USA
BA in Business Economics, 2016
University of California, Los Angeles (UCLA), USA

Experience

Data Scientist

trivago

January 2024 – Present Düsseldorf, Germany

Built large-scale machine learning and data systems for travel pricing and search analytics, including scalable quantile estimation and production ML pipelines

Research Assistant

EPFL - NLP Lab

January 2023 – January 2024 Lausanne, Switzerland

Developed LLM-based workflows for skill extraction and matching across job postings, course catalogs, and resumes

Graduate Research and Teaching Assistant

Duke University

January 2022 – January 2023 Durham, United States

Research at CEI Lab: Implemented baseline models from literature and evaluated defenses against adversarial model extraction in vertical federated learning systems

Teaching at MIDS and Fuqua: Held weekly office hours for Data Engineering Systems, Data Analysis at Scale in the Cloud, and Fraud Analytics courses

Data Science Intern

Stitch Fix

January 2022 – January 2022 San Francisco, United States

Explored integration of incorporating external fashion trends (NLP task) into our historical-data-based forecasting models

Senior Tax Consultant, Tax Staff

January 2017 – January 2021 San Francisco, United States

Led data-driven R&D tax credit analyses using large client datasets across financial and technology sectors

Teaching Assistant

UCLA

January 2014 – January 2016 Los Angeles, United States

Assisted teaching in taxation and business law courses, leading office hours and grading exams and assignments

Publications

ModelGuard: Information-Theoretic Defense Against Model Extraction Attacks

Proposed novel defense against adaptive model extraction attacks through prediction perturbation by leveraging information theory.

Minxue Tang, Anna Dai, Louis DiValentin, Aolin Ding, Amin Hass, Neil Zhenqiang Gong, Yiran Chen, Hai "Helen" Li

August, 2024 USENIX Security 2024

JobSkape: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching

Developed a framework to generate synthetic job postings using LLMs to address the lack of annotated job posting data that support skill extraction and matching tasks.

Anna Dai, Antoine Magron, Mike Zhang, Syrielle Montariol, Antoine Bosselut

March, 2024 NLP4HR (EACL 2024)

Course Recommender Systems Need to Consider the Job Market

Leveraged LLMs in NLP pipeline to extract skill and match them to a known taxonomy from job postings, course descriptions, and resumes and compared greedy heuristics-based and reinforcement learning-based recommendation systems to recommend courses to job seekers based on their resume and job postings.

Jibril Frej, Anna Dai, Syrielle Montariol, Antoine Bosselut, Tanja Käser

January, 2024 SIGIR 2024 Perspectives

PlugVFL: Robust and IP-Protecting Vertical Federated Learning against Unexpected Quitting of Parties

Research on robustness of vertical federated learning convolutional models against performance and IP leakage risks when nactive parties unexpectedly quit during deployment

Jingwei Sun, Zhixu Du, Anna Dai, Saleh Baghersalimi, Alireza Amirshahi, David Atienza, Yiran Chen

March, 2023 preprint

Projects

Drug Diversion Detection (Capstone Keynote)

As my master’s capstone project, I worked with my team of four to develop a machine learning model to detect drug diversion by anesthesiologists from the Duke University Hospitals.

Predict the Look @ SFIX

As a member of the Algorithms team at Stitch Fix, I worked on a project to predict fashion trends based on external data sources to better inform our buyers and designers.

Contact

Please reach out to me if you have any questions or would like to collaborate!