cv
Basics
| Name | Liancheng Gong (Krystal) |
| lianchenggong0224@gmail.com |
Education
-
2025.08 - Present College Park, MD
-
2022.08 - 2024.05 Philadelphia, PA
MSE
University of Pennsylvania
Data Science
- Big Data Analytics
- Statistics for Data Science
- Database and Information Systems
- Intro to Software Development
- Principles of Deep Learning
- Artificial Intelligence
- Ethical Algorithm Design
-
2018.08 - 2022.05 NYC, Abu Dhabi, Shanghai
B.S.
New York University
Data Science
- Probability and Statistics
- ODE
- Intro to Math Modeling
- Data Structures
- Machine Learning
- Information Visualization
- NLP
- Algorithms
- Decision Making Under Uncertainty
- Human-Centered Data Science
Awards
- 2026
Dean’s Fellowship
University of Maryland
Work
-
2024.09 - 2025.07 Philadelphia, PA
Researcher (with Prof. Harry Zhang)
Drexel University, Computer Science
- Structured LLM outputs into PDDL domain/problem files for verifiable planning
- Iteratively refined outputs with environment feedback; analyzed recurring errors; tried memory/partial-editing
-
2024.08 - 2025.07 Philadelphia, PA
Research Coordinator (with Prof. Daniel Hopkins)
Univ. of Pennsylvania, Political Science
- Analyzed polls/exit polls for FiveThirtyEight 2024 coverage
- Tracked US campaign ads and Russian media topics; scraped 2M+ VK posts and built TF-IDF/BERT features
- Raised political-content share from 10%→50% via logistic regression selection
- Designed GPT-based annotation/translation (≈90% agreement with humans)
- BERTweet finetune on symbolic rhetoric (e.g., "us vs them")
-
2024.02 - 2024.05 Data Scientist (with Yuxuan Zhang, Regina Ruane)
UPenn, Computational Social Science Lab
- Bias tracking on topics (Biden’s age, NATO); automated ETL for Nielsen streams
- Maintained AWS DB; standardized schemas and network names
-
2023.02 - 2023.12 Graduate Research Assistant
UPenn, Atlas (with Mark Whiting)
- PDF segmentation + QA with LLMs (DMN/Parallel Context)
- Curated 300+ papers and 300+ questions; improved coverage and accuracy
Projects
-
Machine QA on Chinese Judicial RC
- Span-extraction MRC system
-
Colorize Images with Deep Learning
- Compared ResNet, GAN, VAE
-
Customer Lifecycle (NYU × HSBC)
- Segmentation, churn prediction, targeted recs
-
Max Car Speed in Rain
- Visibility modeling + safe-speed estimation
Volunteer
-
2022.10 - 2023.05
Skills
| Programming | |
| Python | |
| R | |
| SQL | |
| Java |
| Libraries | |
| NumPy | |
| Pandas | |
| SciPy | |
| scikit-learn | |
| PySpark | |
| Matplotlib | |
| Seaborn | |
| PyTorch | |
| TensorFlow |
| Tools | |
| AWS (RDS/SageMaker/S3/EMR) | |
| MySQL | |
| MongoDB | |
| Tableau | |
| Power BI | |
| Git | |
| Linux | |
| Stata | |
| MATLAB | |
| ETL |