Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Hi, I’m Yicen Ye, a data scientist with a strong foundation in Machine Learning, Data Science, and statistical modeling, built through roles in tech, finance, and research. I’m currently pursuing my M.S. in Data Science at Brown University, after earning my B.A. in Mathematics and Computer Science from New York University. My education and experience across the U.S. and China have shaped a multidisciplinary approach to solving real-world problems through data-driven insights. I enjoy turning messy data into actionable insights and collaborating with product, research, and business teams to drive evidence-based decisions and measurable impact. My technical toolkit includes Python (pandas, NumPy, scikit-learn, TensorFlow), SQL (MySQL, Hive, Spark, Hadoop, MongoDB), and cloud and DevOps tools such as Git, Docker, Databricks, and AWS. I also have hands-on experience with Generative AI and Large Language Models (LLMs), including model fine-tuning and applications for NLP and computer vision tasks. I’ve built end-to-end data pipelines, optimized Machine Learning models through feature engineering and hyperparameter tuning, and developed interpretable dashboards and reports that connect data to strategic decisions. I’m passionate about leveraging data and AI to enhance user experience, accelerate product growth, and create measurable business outcomes.…Hi, I’m Yicen Ye, a data scientist with a strong foundation in Machine Learning, Data Science, and statistical modeling, built through roles in tech, finance, and research. I’m currently pursuing my M.S. in Data Science at Brown University, after earning my B.A. in Mathematics and Computer Science from New York University. My education and experience across the U.S. and China have shaped a multidisciplinary approach to solving real-world problems through data-driven insights. I enjoy turning messy data into actionable insights and collaborating with product, research, and business teams to drive evidence-based decisions and measurable impact. My technical toolkit includes Python (pandas, NumPy, scikit-learn, TensorFlow), SQL (MySQL, Hive, Spark, Hadoop, MongoDB), and cloud and DevOps tools such as Git, Docker, Databricks, and AWS. I also have hands-on experience with Generative AI and Large Language Models (LLMs), including model fine-tuning and applications for NLP and computer vision tasks. I’ve built end-to-end data pipelines, optimized Machine Learning models through feature engineering and hyperparameter tuning, and developed interpretable dashboards and reports that connect data to strategic decisions. I’m passionate about leveraging data and AI to enhance user experience, accelerate product growth, and create measurable business outcomes.

Yicen(Anita) Ye

Data Scientist, Programmer, AI Engineer, +2





Hi, I’m Yicen Ye, a data scientist with a strong foundation in Machine Learning, Data Science, and statistical modeling, built through roles in tech, finance, and research. I’m currently pursuing my M.S. in Data Science at Brown University, after earning my B.A. in Mathematics and Computer Science from New York University. My education and experience across the U.S. and China have shaped a multidisciplinary approach to solving real-world problems through data-driven insights. I enjoy turning messy data into actionable insights and collaborating with product, research, and business teams to drive evidence-based decisions and measurable impact. My technical toolkit includes Python (pandas, NumPy, scikit-learn, TensorFlow), SQL (MySQL, Hive, Spark, Hadoop, MongoDB), and cloud and DevOps tools such as Git, Docker, Databricks, and AWS. I also have hands-on experience with Generative AI and Large Language Models (LLMs), including model fine-tuning and applications for NLP and computer vision tasks. I’ve built end-to-end data pipelines, optimized Machine Learning models through feature engineering and hyperparameter tuning, and developed interpretable dashboards and reports that connect data to strategic decisions. I’m passionate about leveraging data and AI to enhance user experience, accelerate product growth, and create measurable business outcomes.…Hi, I’m Yicen Ye, a data scientist with a strong foundation in Machine Learning, Data Science, and statistical modeling, built through roles in tech, finance, and research. I’m currently pursuing my M.S. in Data Science at Brown University, after earning my B.A. in Mathematics and Computer Science from New York University. My education and experience across the U.S. and China have shaped a multidisciplinary approach to solving real-world problems through data-driven insights. I enjoy turning messy data into actionable insights and collaborating with product, research, and business teams to drive evidence-based decisions and measurable impact. My technical toolkit includes Python (pandas, NumPy, scikit-learn, TensorFlow), SQL (MySQL, Hive, Spark, Hadoop, MongoDB), and cloud and DevOps tools such as Git, Docker, Databricks, and AWS. I also have hands-on experience with Generative AI and Large Language Models (LLMs), including model fine-tuning and applications for NLP and computer vision tasks. I’ve built end-to-end data pipelines, optimized Machine Learning models through feature engineering and hyperparameter tuning, and developed interpretable dashboards and reports that connect data to strategic decisions. I’m passionate about leveraging data and AI to enhance user experience, accelerate product growth, and create measurable business outcomes.

Available to hire

Hi, I’m Yicen Ye, a data scientist with a strong foundation in Machine Learning, Data Science, and statistical modeling, built through roles in tech, finance, and research.

I’m currently pursuing my M.S. in Data Science at Brown University, after earning my B.A. in Mathematics and Computer Science from New York University. My education and experience across the U.S. and China have shaped a multidisciplinary approach to solving real-world problems through data-driven insights.

I enjoy turning messy data into actionable insights and collaborating with product, research, and business teams to drive evidence-based decisions and measurable impact. My technical toolkit includes Python (pandas, NumPy, scikit-learn, TensorFlow), SQL (MySQL, Hive, Spark, Hadoop, MongoDB), and cloud and DevOps tools such as Git, Docker, Databricks, and AWS. I also have hands-on experience with Generative AI and Large Language Models (LLMs), including model fine-tuning and applications for NLP and computer vision tasks.

I’ve built end-to-end data pipelines, optimized Machine Learning models through feature engineering and hyperparameter tuning, and developed interpretable dashboards and reports that connect data to strategic decisions. I’m passionate about leveraging data and AI to enhance user experience, accelerate product growth, and create measurable business outcomes.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Language

English

Fluent

Chinese

Advanced

Work Experience

Data Science Intern, Product, Privacy Team at TikTok Inc.

September 1, 2025 - September 1, 2025

Led acausal inference analysis in Python to evaluate the impact of comment privacy settings on user experience, applying propensity score matching, difference-in-differences, and learner-based methods to estimate ATE and CATE across country-level heterogeneous effects; observed +5.20% session duration and +5.75% video views, indicating a positive causal relationship. Conducted cross-country, cross-dimensional segmentation to identify user groups with stronger demand for privacy changes and validated hypotheses via SQL-derived case studies. Delivered AB test reports on UK compliance policy; identified 16–17-year-old users as most impacted, informing PM decisions and enabling a successful feature launch. Performed user journey analysis with Sankey visualizations to locate loss points and conversion gaps, identifying UK U18 users as experiencing larger drop-offs. Designed, registered, and validated event tracking; built dashboards for Privacy products; collaborated with PMs to align met

Financial Engineering Analyst Intern at Changjiang Securities

August 1, 2023 - August 1, 2023

Built automated data preprocessing pipelines for 80k+ structured and unstructured financial data, including web scraping (BeautifulSoup, Scrapy); reduced preprocessing time and accelerated predictive modeling. Developed and optimized XGBoost and Random Forest models for fund return forecasting with multi-factor analysis; applied differential evolution for hyperparameter tuning, reducing RMSE by 17%. Designed a Python backtesting framework (pandas, NumPy, statsmodels) integrating time-series analysis and factor models to improve Sharpe Ratio by 24% and improve simulation efficiency. Conducted NLP-driven topic modeling (LDA, NMF) and sentiment analysis on 50k+ forum discussions, detecting early signals of factories’ overseas relocations to inform portfolio allocation.

Data Scientist Research Assistant at Citizens Bank & Brown University

May 1, 2025 - May 1, 2025

Led a ML project on fraud detection; developed and evaluated predictive models (XGBoost, Random Forest, Neural Network) using historical RDI data to predict check deposit returns, improving recall by 21%. Performed EDA, engineered time-series and behavioral features (deposit frequency, rolling averages, volatility), refining fraud signals and boosting model robustness. Delivered interpretable outputs using feature importance and coefficients, identifying key predictors (minimum check amount, monthly transaction count) as indicators of fraud risk.

Data Scientist Intern at Yingda Insurance Asset Management

August 1, 2022 - August 1, 2022

Developed ARIMA models for steel rebar futures forecasting with statistical diagnostics (ADF, white noise, residual checks) to ensure robust assumptions. Built ML pipelines for price movement prediction, engineering lag and rolling indicators, and optimizing models with GridSearchCV, achieving 85% precision and 81% recall in trend classification.