Skip to content
View Be1an001's full-sized avatar

Achievements

Achievement: Pull Sharkx2

Achievements

Achievement: Pull Sharkx2

Block or report Be1an001

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
Be1an001/README.md

Hi, I'm Cheng Liu 👋

Analytics graduate from Northeastern University, Silicon Valley (Applied Machine Intelligence, GPA 3.93). Previously a Java software engineer in Taipei. Now focused on data analysis, machine learning, and building decision-support tools that non-technical stakeholders can actually use.

🛠️ Tech Stack

Languages

Python SQL R Java

ML & Analytics

scikit-learn XGBoost Pandas SHAP

Tools & Platforms

Streamlit Tableau MySQL Git

📌 Featured Projects

🚀 Salifort Retention Risk Explorer A 9-page Streamlit decision-support app extended from a notebook attrition analysis. Includes PACE Navigator and an MLOps Lab covering FastAPI, Docker, MLflow, Airflow scaffold, and CI. 🔗 Live Demo

📊 Pharmacy Claims Data Warehouse Star schema design in MySQL with dimension/fact tables, foreign-key constraints, and CTE + window-function reporting queries.

🔬 Semiconductor Pass/Fail Prediction Leakage-safe ML workflow on UCI SECOM sensor data with class-imbalance handling and threshold tuning.

✈️ Nvidia Risk Management Analysis Portfolio version of my ALY6130 project on NVIDIA risk management using risk scoring, heat maps, scenario modeling, and Monte Carlo simulation.

🚗 Waze Churn Modeling Five-model comparison with calibration review, threshold tuning, and CatBoost SHAP explainability.

🌱 Background

I took a non-linear path from advertising design, field work, information management, Java engineering, to a master's in analytics in the US. Each step added something useful: engineering rigor from the Java work, stakeholder communication from sponsor projects, and a habit of asking what the result is actually for.

🎯 Currently

  • 🔍 Looking for Data Analyst, BI, and applied ML roles in Taiwan
  • 📚 Working on Google Business Intelligence Certificate

📍 Taiwan  |  📧 akbakb480000@gmail.com  |  🔗 LinkedIn  |  🚀 Live Demo App

Pinned Loading

  1. nvidia-risk-management-analysis-python nvidia-risk-management-analysis-python Public

    Portfolio version of my ALY6130 project on NVIDIA risk management using risk scoring, heat maps, scenario modeling, and Monte Carlo simulation.

    Jupyter Notebook

  2. salifort-motors-attrition-modeling-python salifort-motors-attrition-modeling-python Public

    Cost-aware employee attrition modeling project based on the Salifort Motors case, with operational and survey-rich modes, SHAP explainability, and HR-focused retention insights.

    Jupyter Notebook

  3. nyc-taxi-generous-tipper-classification-python nyc-taxi-generous-tipper-classification-python Public

    Public portfolio rewrite of the Automatidata project using official NYC Open Data, Colab, and XGBoost to predict generous tipper trips.

    Jupyter Notebook

  4. salifort-retention-risk-explorer-streamlit salifort-retention-risk-explorer-streamlit Public

    Streamlit app for operational HR attrition screening and decision support based on the Salifort Motors portfolio case.

    Python

  5. secom-fail-screening-streamlit secom-fail-screening-streamlit Public

    Interactive Streamlit portfolio app for SECOM semiconductor fail-screening benchmark, threshold trade-off analysis, explainability, and MLOps-lite demonstration.

    Python

  6. vertex-ai-credit-card-fraud-case-study vertex-ai-credit-card-fraud-case-study Public

    Portfolio case study from EAI6020 using Vertex AI AutoML for credit card fraud detection, with precision-recall evaluation, threshold selection, and business trade-off analysis.