Analyst Intern Big Data

ANYAN LIU

Phone: 1-734-***-**** Email: ************@*******.***

EDUCATION

University of Michigan - Ann Arbor 08/2024-05/2026

Master of Science in Biostatistics; GPA: 3.7/4.0

Courses: Computing with Big Data, Survival Time Analysis, Biostatistical Inference, Generalized Linear Models Hong Kong Baptist University 09/2020-06/2024

Bachelor of Science (Honours) in Statistics from HKBU; Dean’s List Award

Courses: Linear Regression, Experimental Design, Advanced Statistics, Categorical Data Analysis, Data Mining INTERNSHIPS

WeDoctor Tianjin, China 06/2024-08/2024

Position: Health Economics Analyst Intern

Description: Conducted a cost-effectiveness analysis of a comprehensive chronic disease management program, providing value evidence and strategic recommendations for clinical and policy.

Led a real-world data (RWD) study based on 15,638 patients over 6 months, applying QALY as the health utility metric to evaluate clinical outcomes.

Estimated ICER using a Markov model to simulate disease progression, incoporating transition probabilities and utility weights from local epidemiological and claims data.

Performed probabilistic sensitivity analysis (PSA) and genereated CEACs to assess model robustness.

Applied PSM to control for baseline confounding and improve internal validity of comparative outcome analyses.

Compiled research findings into policy briefs and value communication materials to support reimbursement negotiations and program implementation.

The Third Affiliated Hospital, Sun Yat-sen University Guangzhou, China 06/2023-08/2023 Position: Biostatistician Intern

Description: Practiced in the fields of health medicine, statistics and data science, and artificial intelligence.

Designed a neural network-based AI diagnostic scheme for Lymphoma Large Cell.

Used R to study the effect of angle of progression (AOP) on mode of delivery:

Filled in missing values and tabulated baseline characteristics;

Under the analytical framework of marginal structural model, used propensity analysis and inverse probability weighting (IPW) to control 24 confounding variables, followed by generalized estimating equation modeling to analyze the effect of AOP on mode of delivery.

Based on 32 EMR variables, compared the performance of predicting hip fracture of Logistic Regression Model and ML models (GBM, RF, XGBoost, and nnet) by using ROC curve, Calibration Plot and sensitivity-specificity metrics. BOE Technology Group Co., Ltd Chongqing, China 06/2022-08/2022 Position: Quality Management Engineer Intern

Description: Reduce the defective rate (from 0.44% to 0.03%) of 35,982 LED screen products.

Performed data cleaning and reduced the dimensionality of data with PCA.

Analyzed the effect of production process variables on product defective rate: ̶ Used K-Means Clustering to divide 35982 data into two clusters. ̶ Implemented PLSDA algorithm using R for assessment of feature importance analysis, and filtered 10 key production process variables from 33 variables by PLSDA Score plot and PLSDA Loading plot. RESEARCH EXPERIENCE

Algorithm Design for Disease Risk Control Based on Asymmetric Statistical Learning 10/2022-01/2024 Teamwork (Team Leader) Zhuhai, China

Description: Handled imbalanced data and asymmetric error to reduce the false-negative rate in breast cancer diagnostics.

Determined the classification paradigm, i.e. choosing Neyman-Pearson Paradigm.

Dealt with unbalanced data through resampling techniques and selected variables using LASSO.

Optimized the underlying machine learning classifier algorithm to reduce the false negative rate from 0.14 to 0.008: ̶ Used Neyman-Pearson Umbrella Algorithm to build NP-LDA classifier. ̶ Built NP-sLDA classifier for high-dimensional data with Neyman-Pearson Umbrella Algorithm. ̶ Built pNP-LDA classifier with parametric threshold algorithm to address minimum sample size requirements.

Evaluated the models with ROC-Band.

Achievement: The project has been established in the Science and Technology Innovation Cultivation Program in China, and received 15,000 RMB of grant funds.

SKILLS & AWARDS

̶ Computer: R Language, Python, C Language, MATLAB, LaTeX, SPSS, SQL, Microsoft Office Specialist ̶ Math: Honorable Mention, Mathematical Contest in Modeling(MCM)

Contact this candidate