Skip to content
View jiaxiang-cheng's full-sized avatar
🎯
Focusing
🎯
Focusing
147 followers · 25 following

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Achievements

Achievement: Starstruckx2Achievement: Pull Shark

Block or report jiaxiang-cheng

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
jiaxiang-cheng/README.md

banner

Fujikawaguchiko, Yamanashi, Japan

👋 Hi, I’m Jiaxiang Cheng

Data Scientist @ American Express | Ph.D. (NTU, 2025)

📍 Singapore
📬 jiaxiang.cheng@outlook.com | 🔗 LinkedIn

🚀 About Me

I am a Data Scientist at American Express, working on applying machine learning and statistical modeling to real-world financial and customer behavior problems.

I completed my Ph.D. at Nanyang Technological University (NTU) in 2025, where my research focused on machine learning for prognostics, reliability, and survival analysis, with applications in remaining useful life (RUL) prediction and industrial systems.

My interests sit at the intersection of:

  • 📊 Applied machine learning & data science
  • 🔍 Risk modeling, prediction, and decision support
  • 🧠 Deep learning for time series & survival analysis
  • 🛠️ Translating research models into production-ready solutions

🏢 Current Role

Data Scientist — American Express

  • Research and development of machine learning models for customer behavior and risk analysis
  • Model performance monitoring and governance automation
  • Data-driven insights to support personalized offers and decision-making

🎓 Academic Background

Ph.D., Nanyang Technological University (NTU) — Graduated 2025

  • Machine Learning for Prognostics & Health Management
  • Survival Analysis, Deep Learning, Reliability Modeling

🏆 Best Paper Award, PHM Asia-Pacific 2023

Deep Learning-Enabled Statistical Model Estimation for Power Transformers with Censoring and Truncation Problems

⭐ Selected Projects

📦 Machine Learning & Modeling

Project Description
KAN-for-Survival-Analysis Extends Cox models with symbolic nonlinear log-risk functions for survival analysis.
PyTorch-Transformer-for-RUL-Prediction Transformer-based architecture for RUL prediction on NASA C-MAPSS datasets.
PyTorch-LSTM-for-RUL-Prediction LSTM models for remaining useful life estimation.
PyTorch-CNN-for-RUL-Prediction CNN-based RUL prediction framework.
PyTorch-PDQN-for-Digital-Twin-ACS Reinforcement learning control for digital twin conveyor systems.

These repositories focus on reproducible experiments, clear baselines, and practical ML implementations.

🛠 Tech Stack

Languages
Python · R · MATLAB

ML / Data Science
PyTorch · scikit-learn · Pandas · NumPy · Time Series Modeling

Concepts
Deep Learning · Survival Analysis · Risk Modeling · Model Monitoring

📫 Connect with Me

I’m always happy to connect on data science, applied ML, or research-to-production topics.

📧 Email: jiaxiang.cheng@outlook.com
💼 LinkedIn: https://www.linkedin.com/in/jiaxiang-cheng/

🌱 Beyond Work

🎶 Music & singing · 📸 Photography · 🧠 Lifelong learning

Pinned Loading

  1. KAN-for-Survival-Analysis KAN-for-Survival-Analysis Public

    CoxKAN: Extending Cox Proportional Hazards Model with Symbolic Non-Linear Log-Risk Functions for Survival Analysis

    Jupyter Notebook 1

  2. PyTorch-Transformer-for-RUL-Prediction PyTorch-Transformer-for-RUL-Prediction Public

    Transformer implementation with PyTorch for remaining useful life prediction on turbofan engine with NASA CMAPSS data set. Inspired by Mo, Y., Wu, Q., Li, X., & Huang, B. (2021). Remaining useful l…

    Python 299 52

  3. PyTorch-LSTM-for-RUL-Prediction PyTorch-LSTM-for-RUL-Prediction Public

    PyTorch implementation of remaining useful life prediction with long-short term memories (LSTM), performing on NASA C-MAPSS data sets. Partially inspired by Zheng, S., Ristovski, K., Farahat, A., &…

    Python 179 25

  4. Hedging-Impermanent-Loss-in-Uniswap-V3 Hedging-Impermanent-Loss-in-Uniswap-V3 Public

    By DeFiNER, Decentralized Finance Navigates Every Route. A Solution Framework for Modeling and Hedging Impermanent Loss and Dynamic Liquidity Provision Using Deep Reinforcement Learning in Uniswap …

    Jupyter Notebook 1 2

  5. PyTorch-CNN-for-RUL-Prediction PyTorch-CNN-for-RUL-Prediction Public

    PyTorch implementation of CNN for remaining useful life prediction. Inspired by Babu, G. S., Zhao, P., & Li, X. L. (2016, April). Deep convolutional neural network-based regression approach for est…

    Python 102 18

  6. PyTorch-PDQN-for-Digital-Twin-ACS PyTorch-PDQN-for-Digital-Twin-ACS Public

    PyTorch implementation of RIC for conveyor systems with Deep Q-Networks (DQN) and Profit-Sharing (PS). Wang, T., Cheng, J., Yang, Y., Esposito, C., Snoussi, H., & Tao, F. (2020). Adaptive Optimizat…

    Python 14 3