Skip to content
View martin-he543's full-sized avatar
㊗️
Relaxing
㊗️
Relaxing

Highlights

  • Pro

Block or report martin-he543

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.

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
martin-he543/README.md

Hi there 👋

Business Analytics Student | Physics Enthusiast | ML Enthusiast

I am a second-year Business Analytics and Finance student at Bayes Business School, bridging the gap between the mathematical rigour of a Theoretical Physics foundation from Imperial College London and advanced predictive modelling.


🚀 A Supercut: What I’ve Worked On

  • NLP & Semantic Search: Developed a vector-based search engine using BERT, FastAPI, and Docker during my internship at Perforce Software.
  • Multi-modal AI: Building a recommendation system for Spotify using PyTorch to process audio previews, lyrics, and album art via CNNs and Transformers.
  • FinTech & Trading: Explored arbitrage, market-making, and market movement prediction using generational neural networks during the Optiver "Ready, Trader, Go" competition.
  • Social Impact: Co-founded Altruist, the "Bloomberg Terminal for Charities," winning the Innovate Hackathon with a responsive React/Firebase architecture.

🛠 Tech Stack

  • Languages: Python (PyTorch, TensorFlow, Scikit-Learn, Pandas), R, SQL (PostgreSQL, MongoDB), JavaScript (React, TypeScript), Rust.
  • Tools: Docker, Git, Power BI, Tableau, $\LaTeX$, EViews, FastAPI.
  • Specialties: Financial Econometrics, Computer Vision (OpenCV), Supervised/Unsupervised ML, Deep Learning.

🏆 Achievements

  • Winner, Bayes Business Analytics Data Olympics 2025.
  • Bayes Academic Scholarship (awarded to the top 10%).
  • Creator of Royana Font, which has reached 10,000+ downloads and is used globally in commercial packaging and books.

🍱 Beyond the Code

  • 🎹 Musician: I enjoy playing the piano, as well as composing, transcribing, and organising events.
  • 🚴 Not Just Academics: I'm into long-distance cycling, running, and hitting the gym. Also basketball
  • 🌍 Polyglot: I’m a native English speaker, advanced in French (C1) and Chinese (HSK 5), and currently learning Japanese (N3), Italian (B1), Spanish (A2), Norwegian (A1), Dutch (A1), Latin (> GCSE), and Ancient Greek (> GCSE).

📫 Let's Connect!

  • Location: Surbiton, Greater London, UK
  • E-mail: Please contact me on socials for further information.

Pinned Loading

  1. novozymes-enzyme-stability-prediction-kaggle-2022 novozymes-enzyme-stability-prediction-kaggle-2022 Public

    The Kaggle team for the Novozymes Enzyme Stability Prediction Machine Learning Hackathon, 2022. Run through Kaggle.

    Jupyter Notebook 8 1

  2. classics-cheat-sheets classics-cheat-sheets Public

    Summary grammar and modified DVLs for OCR's Classical Greek (9-1), Latin (9-1) GCSEs, from the 2016 syllabi. Used as part of educational resources in Tiffin School and the Kingston Academy.

    3

  3. python-machine-learning python-machine-learning Public

    Machine Learning (ML) in Python.

    Jupyter Notebook 3

  4. spotify_x411k spotify_x411k Public

    Building a recommendation system based on Spotify data, augmented with MP3 30-second previews, album art, and lyrics. Employed PyTorch to create CNN-based, and transformer-based models.

    Jupyter Notebook 1