Victoria Farkas
  • Home
  • CV
  • Projects
  • Beyond Data
  • LinkedIn
  • Email

CV

Victoria Farkas

Contact

victoriafarkas9@gmail.com

LinkedIn

Vancouver, BC

Languages: English (native) · French (B1 Certified) · Hungarian (heritage speaker)


Education

Master of Data Science (MSc.)
University of British Columbia · 2025 – Present

  • Recipient of the $10,000 Domestic Student Excellence Scholarship, awarded for outstanding achievement in data science

Bachelor of Science, Behavioural Neuroscience
University of British Columbia · 2019 – 2024

  • Coursework spanned research statistics, experimental design, human subjects ethics, and cognitive systems

Cours de Civilisation Française
La Sorbonne, Paris · Jan – Jun 2019

  • Full academic immersion; certified in conversational French (A2/B1)

Technical Skills

Programming & Analysis

  • Python (Pandas, PyTorch, scikit-learn, NumPy, OpenCV), R, SQL, C, SPSS

Tools & Platforms

  • Tableau, Git, Plotly, Shiny, Streamlit, Docker

Domains

  • Health data governance, privacy-preserving data linkage, machine learning, statistical modelling, UI/UX design

Certifications

  • TCPS 2: CORE — Tri-Council Policy Statement on Ethical Conduct for Research Involving Humans (Sep 2020)

Profile

Master of Data Science student at UBC with a strong foundation in rigorous statistical modelling and full-stack software development. Experienced in engineering secure data pipelines, managing population-scale datasets (10,000+ variables), and building interactive frontend data applications. Brings a track record of leading data intake projects across major government and health institutions, with deep familiarity with privacy-preserving methodology and data governance frameworks. Multilingual communicator adaptable to international and fast-paced environments.


Work Experience

Data Scientist · UBC Data Science Club · Dec 2025 – Present

  • Embedded as data scientist on a Computer Vision research project led by a Master of Physiotherapy candidate at UBC
  • Developed a classification pipeline to identify exercise types and evaluate form quality from raw video data
  • Optimized feature selection by identifying key joint angles and spatial relationships, significantly reducing the dimensionality of the input data without sacrificing predictive power

Data Access / Management Assistant · Population Data BC · May 2023 – Sep 2025

  • Appointed project lead for the provincial intake of the Canadian Longitudinal Study on Aging (CLSA), a novel, first-of-kind dataset from the Canadian Institutes of Health Research comprising 10,000+ variables, coordinating cross-functional validation, documentation, and integration
  • Led dataset management and data intakes on behalf of major institutional stewards including BC Cancer, Immigration, Refugees & Citizenship Canada (IRCC), and the H.E.L.P. initiative
  • Contributed to finalising the DAR 2.0, an updated data request platform used by health researchers across Canada, participating in UAT and stakeholder feedback cycles
  • Collaborated across units with data stewards, researchers, and policy professionals to improve analyst access to linked administrative health data

Graduate Teaching Assistant (CPSC 100) · UBC Faculty of Science · Aug 2025 – Present

  • Responsible for instruction and lab lesson design in introductory computing concepts for a large undergraduate cohort

Teaching Fellow (PSYC 218) · UBC Faculty of Arts · Jan – May 2024

  • Awarded a graduate-level teaching role following a course grade of 98%, a position normally reserved for graduate students
  • Designed and delivered lectures on SPSS and core statistics topics (linear regression, ANOVA) to approximately 200 students

Teaching Assistant (APSC 160) · UBC Faculty of Applied Science · Sep – Dec 2023

  • Assisted in teaching a 700+ student introductory C programming course covering documentation and electrical circuitry applications
  • Appointed Head TA during final exam invigilation; authored new exam questions testing intermediate skills in strings, functions, and algorithms

Teaching Assistant (CPSC 100) · UBC Faculty of Science · Jul – Sep 2023

  • Hosted independent lab sessions, office hours, and tutoring for 200+ students in introductory programming and algorithmic problem-solving

Research Assistant · UBC Social Cognition & Emotion Lab · Apr – Sep 2023

  • Collected and managed over 250 participant datasets; oversaw recruitment, debriefing, and study validity protocols under real-world conditions

Leadership & Community Involvement

Admissions Committee Member · UBC Master of Data Science · Nov 2025 – Present

  • Reviewed and evaluated applicant submissions for the MDS programme as a student committee member

Social Student Representative · UBC Master of Data Science · Sep – Dec 2025

  • Selected as one of six student representatives for MDS Cohort 10; responsible for community-building, social programming, and networking events
  • Organised a cohort hackathon and secured sponsorship from an AI research lab (CAIDA)

Judge & Mentor · Women in Data Science @ UBC · Oct – Nov 2024

  • Evaluated 11 submissions across two rounds of the WiDS case competition, assessing model performance, data cleaning, and results communication
  • Mentored current UBC students at the WiDS Alumnight on networking, job applications, and data science career pathways

Events Director · UBC Women in Data Science Club · May 2023 – Jun 2024

  • Planned and produced panel events featuring industry professionals from Google, Shopify, and Procter & Gamble
  • Secured sponsorships from local companies and founded a recurring alumni mentorship event

VP Creative · UBC Dance Horizons · May 2020 – May 2023

  • Led creative direction and event production for a 20–50 member club; managed performance planning, content, and member coordination across three years

VP Creative & Media · UBC Unlimited Dance Club · Sep 2021 – May 2023

  • Held simultaneous executive creative role across two clubs; coordinated overlapping event calendars and media production

Provincial Page · Legislative Assembly of Ontario · Mar – May 2013

  • Served in the Ontario Legislature assisting Members of Provincial Parliament; present for and assisted in delivery of the 2013 Provincial Budget

Projects & Competitions

Multimodal pCR Prediction for Breast Cancer · National Canadian Medical Datathon 2026 · [3rd Place] · Mar 2026

  • Designed an end-to-end multimodal deep learning pipeline to predict pathologic complete response (pCR) in breast cancer patients undergoing Neoadjuvant Chemotherapy (NAC)
  • Engineered a computer vision workflow utilizing OpenCV to extract critical spatial biomarkers: nuclear density, edge complexity, and clump count, from high-resolution Whole Slide Images (WSIs)
  • Built and optimized a custom Keras neural network trained on a multimodal dataset of extracted digital pathology features and traditional clinical history, successfully outperforming tabular-only baseline models
  • Achieved an overall predictive accuracy of 78%, balancing a 92% precision rate for complete responses with a 93% recall rate for partial responses to align with clinical triage needs

Cursor AI Hackathon · Voxolith · Feb 2026

  • Built a full-stack, interactive 3D visualisation tool for complex neuro-spatial data using Python, Plotly, and Streamlit
  • Designed a dynamic frontend UI with hover-over tooltips and region-highlighting, bridging backend data with accessible user interfaces
  • Implemented stochastic data generation using FastNoise2 and Simplex noise functions, creating complex, non-linear environmental models for terrain synthesis

nwHacks 2026 — SightQuest · Jan 2026

  • Orchestrated a high-performance backend workflow to ingest and process multimodal data streams, utilizing Python to bridge raw sensory input with generative AI models
  • Integrated the Gemini 3 Pro API to perform zero-shot visual reasoning and complex task planning, enabling the system to interpret 3D environments and provide context-aware feedback

BOLT Datathon · [Semi-Finalist] · Oct 2025

  • Sole data scientist and programmer; developed a pipeline to consolidate siloed datasets, comprising stadium attendance, membership tiers, and product purchases, using Pandas for complex joins and data cleaning to create a 360-degree customer view
  • Implemented a K-Means Clustering model to segment the fanbase into distinct behavioral personas, enabling targeted marketing and retention strategies

nwHacks 2024 — Biomedical Waste Management System · [Track Winner] · Jan 2024

  • Designed a digital biomedical waste management system for hospital implementation; placed top 3 in the Environmental & Sustainability track

BizInnovate — Pacific Conference on Artificial Intelligence · [1st Place / 18 teams] · Apr 2023

  • Supported the business presentation of a machine learning model predicting regional water quality using geospatial survey data and satellite image feature extraction

UBC girlCode × Aritzia Hackathon · Jan 2023

  • Delivered an original front-end and UI/UX product case project within a 24-hour sprint