Machine Learning Data Scientist

YEN-CHUN (CALVIN), CHEN

608-***-**** • linkedin.com/in/yenchun-chen • Digital Portfolio • *******.******@*****.*** SUMMARY

Experience: Data Scientist/Engineer with 3+ years of experience in network and operation analytics. Skilled in building data pipelines, machine learning models, and data-driven solutions. Programming: Python (Scikit-learn, Pandas, Numpy, Matplotlib, Seaborn, Plotly, Pytorch, Flask, Streamlit), SQL, R Cloud Computing: AWS (Solution Architect Associate Cert), GCP(BigQuery), Snowflake, DBT, Fivetran, Databricks Tools: Machine Learning, ETL, Data Visualization, Tableau, A/B Testing, Statistical Analysis, APIs, Git PROFESSIONAL EXPERIENCE

Boost Mobile Denver, CO 03/23 – Present

Data Scientist, 5G Network Data & Analytics

Tech Stack: AWS(Athena, Redshift, EC2) / Python / SQL (SQL Server, Snowflake) / Tableau / Dataiku / Machine Learning Models / Streamlit

● Achieved a 1M+ subscriber increase and improved key network metrics by integrating anomaly detection, capacity forecasting, and network availability analysis in collaboration with cross-functional teams.

Designed and deployed an end-to-end ML pipeline for anomaly detection (Isolation Forest, MSTL), reducing roaming rates by 5% for over 1 million users, saving $5M, and cutting investigation time from days to seconds.

Developed time series forecasting models (LightGBM, LSTM) for network capacity planning, improving MAPE by 5% and optimizing site build plans and resource allocation.

Developed a 10TB-scale network analytics pipeline using Random Forest, reducing call drop rates by 3% and enhancing wireless transport reliability. (Invention Patent)

● Engineered a Material Requirement Planning Platform with inventory optimization, automated reordering, demand forecasting, and a data-driven dashboard, collaborating with the entire supply chain organization to reduce manual processing time from 5+ hours to minutes.

● Led cost reduction(CapEx / OpEx) initiatives, identifying high-cost activities and uncovering millions in excess costs through statistical analysis and dashboards, presenting findings to senior stakeholders to drive strategies.

● Optimized 100+ retail wireless projects using Mixed-Integer Programming, increasing revenue by 5%, achieving 3% cost savings, and minimizing complexity.

● Automated resolution pipeline for critical integration system failures, reducing ticket resolution time from 10+ hours to under 1 hour, driving national network coverage expansion from 28% to 71%. Lenovo Morrisville, NC 06/22 – 08/22

Data Engineer Intern, Data Management

Tech Stack: Python / Java / Snowflake / PostgreSQL / Linux System / Jira / Rest API

● Developed a Python-based ETL pipeline to monitor data quality across multiple domains, reducing data validation time by 70% and ensuring seamless integration across diverse databases. Generac Madison, WI 01/22 – 05/22

Data Scientist (part-time)

● Processed 55M+ records with PySpark(Databricks), engineered 25+ features, and built predictive models to identify product failure risks, improving accuracy by 10%. Leveraged SHAP to identify machine failure causes. EDUCATION

University of Wisconsin-Madison, Wisconsin School of Business Madison, WI 2021 – 2022 Master of Science in Business Analytics, GPA: 3.9 /4.0

● Key Coursework: Machine Learning, Cloud Computing, Data Technology & Advanced SQL, Data Science Programming, Statistics, Learning Based Methods for Computer Vision Elected Co-President, Data Analytics Club Yuan Ze University, College of Management Taoyuan, Taiwan 2015 – 2019 Bachelor of Business Administration, Concentration - Innovation and Entrepreneurship, Investment Strategy and Financial Market

Contact this candidate