Stephen Yang

Data Geek. Two-year experience with data science/engineering.

Work Experience

Retail Business Services LLC(Ahold Delhaize), Data Engineering Co-op Jun 2023 ~ Now

Improving search engines performance through MDM.
Validation on the pipelines to ensure data completeness in the downstream tasks.
Monitoring the changes on recommended items from cross-sell model. Building framework of data drifting detection, starting from data retrieval, modeling to statistical/hypothetical testing applied on inference data.
Development of Intake process form app to Integrate ticketing requests from different teams.

Skillset : Databricks/Azure Data Factory/Power Automate/Power BI/ETL pipeline/Spark

Taipei Fubon Bank, Data Scientist(FinTech) Jan 2021 ~ Sep 2022

AI Early Warning Mechanism

In collaboration with Taipei City Police Department and Criminal Investigation Bureau, aimed at combating surging fraud activities during the pandemic which involved multiple channels(ATM, Online, and Mobile banking).
Development of ML model to detect potential AML activities and to further succeed in fraud prevention.
Replaced rule-based triggering with ML-based application in criminal investigation; eliminated tens of thousands of false alarms in a single month, optimized precision up to 80%, and significantly cut operational costs.
Promoted ‘intelligent anti-fraud ecosystem’ with Taipei City Government and was reported in Fubon Financial news: link

ETL Pipeline & Banking Business Analysis

Built analytics platform managing client, finance data collected from upstreams and third parties sources(EC, Telecom) Built end-to-end pipelines for reporting.

Skillset : PySpark/Hadoop/Scikit-Learn/Flask API/Beautiful Soup/ODS/Hive/OBIEE/Tableau/GCP(GCS, Dataflow, VMs, Vertex AI)

Apple Daily, Data Analyst Apr 2020 ~ Aug 2020

Digital tacking with GTM as sources for building ETL pipeline on GCP.
BI reporting for assessing KPIs of news articles.
Subscription analysis, churning prediction, and text mining
Skillset : BigQuery/Data Studio/GA360/Google Analytics/GTM/NLTK/Scikit-Learn/LDA

Education

Boston University, Master of Science in Software Development(MSSD) 2023 ~ Present

Master program for developing essential skillset as software developer. Algorithm, Programming Language and System.

Arizona State University, AI and Machine Learning MasterTrack™ Feb 2021 ~ Dec 2021

Online Graduate Certificate Courses: Statistics, Machine Learning, Artificial Intelligence

Institute for Information Industry, Big Data Bootcamp Sep 2019 ~ Feb 2020

Training in big data and development skills and building end-to-end data projects with Python, MySQL and Hadoop.

Tamkang University, Bachelor of Business Administration(BBA) Sep 2013 ~ Jun 2017

Project & Competition

T-Brain Machine Learning Competition 2022 - Anti Money Laundering

Leveraging XGBoost(GBDT) combined with my ML fraud detection experience to succeed in this competition.

Hosted by : E.SUN Bank & TrendMicro (Rank : No.6)

GoDaddy - Microbusiness Density Forecasting Competition

The project is to demonstrate better performance on time series prediction with Optuna framework.

BIRDS 475 SPECIES - IMAGE CLASSIFICATION

Serving Image model as Streamlit web app on GKE. It allows the user to enter the image url link and display output.

Skillset: Streamlit, GKE, CloudBuild, Python, Git, Docker

Spotify ETL Pipeline

Building ETL for Spotify API and automate the workflows through Airflow. Analytics tasks executed with DBT on SnowFlake.

Skillset: Airflow, DBT, Snowflake, Python, Git, Astronomer, Docker

Skills

Machine Language：Python, PySpark, Tensorflow, PyTorch, SQL

Dashboard：Power BI, Tableau

Cloud Service : GCP, Azure, Cloudera

Development Tool: Docker, Jenkins, Git, Airflow, DBT

Certificate

Project Management Professional(PMP)

AI and Machine Learning MasterTrack® Certificate(ASU)

Google Cloud Certified - Professional Data Engineer