Zebing Lyu
Data Analytics/ Data Scientist/ Data Engineer
Paris
Summary
Enthusiastic and well-rounded data graduate from emlyon Business School, with one year of practical experience analyzing data, constructing data pipelines, and applying deep learning models for tech companies such as Deezer. Eager to leverage current expertise and passion for learning to develop data-driven solutions.
Overview
2
2
years of professional experience
6
6
years of post-secondary education
2
2
Certifications
3
3
Languages
Work History
Analytics Engineer Intern
Deezer
9 2023 - 3 2024
- Data Pipeline Modernization: Developed Python and PySpark scripts to integrate data quality tool Soda into data pipelines, configure orchestrator to automate over 30 daily quality checks running against multiple data sources, which supported reliable decision-making by upholding high data quality standards
- Data Analysis: Conducted data analysis using SQL in BigQuery, pinpointing and rectifying critical data quality issues which led to a significant reduction in data-related errors reported by users
- Documentation & Training: Documented data quality solutions, and led comprehensive training workshops for 40+ technical members, boosting cross-team proficiency in maintaining data quality.
Data Scientist (In-Company Project)
ZEALY
04.2023 - 06.2023
- Data Analysis: Conducted data analysis using SQL in Postgres and exploratory data analysis using Python on user and community data
- NLP & Topic Modeling: Utilized Latent Dirichlet Allocation in NLP to uncover topics in text documents, infer word distributions, and assess model performance using coherence and perplexity scores
- Recommender System: Built a collaborative filtering recommender system by exploring similarity matrix to identify similar user profiles and enhance user experience within the platform.
Data Scientist (In-Company Project)
DATACRAFT
01.2023 - 03.2023
- Data Extraction & Database Building: Designed a web scraping module to automate the extraction of data from APIs and developed a graph database using Neo4j
- Data Analysis: Conducted exploratory data analysis using Python on textual publications
- NLP: Created an AI-related corpus by extracting information from lengthy text documents using NLP and cosine similarity to optimize search functionality.
Financial Intern
BLUE STONE ASSET MANAGEMENT
01.2021 - 06.2021
- Financial Analysis: Conducted thorough financial portfolio analysis, generating daily evaluation and forecast reports.
Education
Master of Science - Data Science & Artificial Intelligence Strategy
Emlyon Business School
Paris, France 09.2022 - 04.2024
Exchange Program -
McGill University
Montreal, Canada 05.2023 - 06.2023
Bachelor of Arts - Business English
Beijing Forestry University
Beijing, China 09.2017 - 07.2021
Skills
Business Acumen
Git
R
GCP
AWS
Tableau
Looker Studio
Power BI
Machine learning
Deep Learning
Effective Collaboration
Excellent Communication
Proactive Problem-solving
Critical thinking
Business Acumen
Certification
AWS Academy Cloud Foundations
Timeline
AWS Machine Learning Specialty
07-2023
Exchange Program -
McGill University
05.2023 - 06.2023
Data Scientist (In-Company Project)
ZEALY
04.2023 - 06.2023
AWS Academy Cloud Foundations
03-2023
Data Scientist (In-Company Project)
DATACRAFT
01.2023 - 03.2023
Master of Science - Data Science & Artificial Intelligence Strategy
Emlyon Business School
09.2022 - 04.2024
Financial Intern
BLUE STONE ASSET MANAGEMENT
01.2021 - 06.2021
Bachelor of Arts - Business English
Beijing Forestry University
09.2017 - 07.2021
Analytics Engineer Intern
Deezer
9 2023 - 3 2024