Chuhan Zhang

213-***-**** Los Angeles, CA ad29r6@r.postjobfree.com LinkedIn

EDUCATION

University of Southern California – Los Angeles, CA September 2021 – December 2023 Master of Science in Applied Biostatistics and Epidemiology Relevant Courses: Machine Learning, Database Management, Hypothesis Testing, Data Visualization Minjiang University – Fuzhou, Fujian, China September 2016 – June 2020 Bachelor of Science in Applied Chemistry

WORK EXPERIENCE

USC Norris Comprehensive Cancer Center – Los Angeles, CA Data Scientist Intern May 2022 – August 2022 Explore the relationship between neutrophil-to-lymphocyte ratio (NLR) and SBP:

• Targeted 5K+ patient data to conduct feature selection through a forward search method to filter meaningful features related to cancer prevention and cancer care.

• Compared the effectiveness for extending life with two medicines through survival analysis (Kaplan-Meier); summarized the key finding that BMI has a positive relationship with the lethality rate.

• Utilized the KM curve to evaluate the survival probability based on different stages; leveraged the logistic regression model to analyze and validate the relationship between NLR and SBP Research Factors Associated with Breast Cancer:

• Conducted research on 4024 breast cancer cases, applying six ML models (Logistic Regression, SVC, Decision Tree, Random Forest, AdaBoost, Gradient Boosting) to predict patient outcomes.

• Evaluated random oversampling and SMOTE techniques for handling imbalanced data, with SMOTE demonstrating a 10% increase in accuracy.

• Identified Gradient Boosting as the top-performing model with 90% accuracy.

• Utilized cross-validation and grid search for hyperparameter tuning, ensuring balanced recall and precision through precision-recall curves for improved model assessment. ACADEMIC PROJECTS

The Purchase and Redemption Forecasts-Challenge the Baseline – Los Angeles, CA January 2022 – June 2022

• Aggregated and processed 100k+ users' historical purchase and redemption data from 4 data sources into a MySQL database

• Led a team of 3 to build forecasting models to predict future cash flows based on users' historical purchase and redemption data to help Ant Financial Services Group (AFSG) improve its funds management abilities

• Leveraged Python to conduct data validation, processing, transformation, and integration in pipeline to reduce the model execution time by 4 mins/epoch.

• Developed 10+ systematic forecasting univariate & multivariate models for predictive analysis based on the weighted average of purchase and redemption error (Best model: LSTM) UI Change Implementation for Product Recommendation – Los Angeles, CA January 2022 – June 2022

• Designed and implemented A/B testing experiments for shopify e-commerce platform website products to verify the strategy effectiveness on user preferences, improved product usage rate by 5%

• Delivered customer insights by model optimization and result interpretation resulting in 8% increase in operational efficiency. Business Data Analysis Based on YELP Dataset – Los Angeles, CA December 2022 – February 2022

• Conducted data processing on 1.32 million yelp review data, integrated 6 data sources into one master table through MySQL

• Performed sentiment analysis using Python over 5.26 million reviews by feature vectorization and text mining to adjust business staring, resulting in a 17% lift in staring precision.

• Developed root cause reports decomposed of 3 dimensions to address problems with elite user retention, successfully revealing insights that boosted retention by 12%

Data Science for Public Health and Biomedicine – Columbia University. February 2022 – August 2022

• Conducted correlation analysis through Linear Regression to identify the key factors associated with lung cancer and supported to classify the lung cancer patients.

• Implemented state-of-the-art (SOTA) classification techniques for lung cancer classification branched from CART, Random Forest, GBDT, and XGBoost via Python; achieved the best model performance with 95% accuracy.

• One paper has been accepted by the International Conference on Bioinformatics Engineering. SKILLS & ACTIVITIES

Computer Skills: Python (Scikit-learn, TensorFlow, Keras, Pandas, Seaborn, Matplotlib), SQL, R, MATLAB, SAS, Power BI, Tableau, Stata.

Data Analysis Techniques: Machine Learning Models (Logistic regression, SVM, Decision Tree, Random Forest, K-means, KNN, Neural Network/CNN, Lasso regression, XGBoost), Hypothesis Testing, Data Visualization, Exploratory Data Analysis

Contact this candidate