Skip to content
View sepidakz's full-sized avatar
👾
Focusing
👾
Focusing
0 followers · 1 following

Block or report sepidakz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sepidakz/README.md

Hi, I'm Sepideh (Sep) 👋

Product & Data-Driven Designer based in Utrecht, NL — 10+ years across e-commerce, mobility and fintech. MA in Data-Driven Design (HU Utrecht), BSc in Physics.

I design data-informed products and build the prototypes to prove them. Practice: User Research and Usability Testing · Design Systems · Interaction Design · Information Architecture · Prototyping · A/B Testing and Experiment Design · Behavioral Analysis · Accessibility (WCAG) · Workshop facilitation

🔗 Portfolio · LinkedIn

Toolkit

Languages & Analysis

Python R SQL pandas NumPy scikit-learn Jupyter

Visualisation & BI

Matplotlib Seaborn Power BI Tableau Streamlit

Data Platforms & Product Analytics

Databricks Mixpanel Amplitude

UX & Product Design

Figma FigJam Miro Framer Maze Hotjar Adobe CC Notion

Front-end

HTML5 CSS3 TypeScript

Workflow

Git GitHub Jira Confluence Azure DevOps

Selected Work

  • data-science-work-samples — Three tabular analyses that each reach a negative or corrected result: a churn model that fails a permutation test, a parsing bug that invented a customer segment, and the same audit redone in SQL. Python scikit-learn SQL
  • predictpro-recommender — Modular Python refactor of my MA thesis prototype (built with Monks): TF-IDF content ranking, weighted multi-criteria scoring, and a from-scratch NumPy cosine similarity. Python NumPy

Pinned Loading

  1. predictpro-recommender predictpro-recommender Public

    Modular Python refactor of a thesis prototype: TF-IDF content ranking with a from-scratch NumPy cosine similarity implementation.

    Python

  2. data-science-work-samples data-science-work-samples Public

    Three tabular analyses focused on data quality validation and honest reporting of negative results

    Jupyter Notebook

  3. student-finance-survey-2024 student-finance-survey-2024 Public

    14-item mixed-methods survey on student financial behaviour: instrument, data, analysis, and a critique of my own questionnaire.

    Jupyter Notebook