Yuqian (Zoe) Yang
*** ** ******* ****** 917-***-**** adm07e@r.postjobfree.com
EDUCATION
Long Island University, NY, USA Sep 2016 - May 2019
Bachelor of Science in Finance, GPA:3.5/4.0
Northeastern University, Boston, USA Sep 2019- Apr 2021
Master of Science in Data Analysis, GPA:3.8 /4.0
Coursework: Machine Learning, Healthcare/Pharmaceutical Data and Applications, Predictive Analytics,Data Management and Big Data.
WORK EXPERIENCE
Northeastern University Boston
Research Assistant Sep 2020 – Oct 2020
Analysis of medical cost and related factors in medical insurance industry
Designed the algorithm and identified the important factors that affect healthcare costs through Python and R
Preprocessed Dataset by data cleaning, classification, standardization and feature transformation.
Trained supervised machine learning models including logistic regression, random forest, k-nearest neighbors, and XGBoost,
and applied regularization with optimal parameters to overcome overfitting
Implemented logistic regression and decision tree model to judge the impact of different living habits on medical expenses
Optimized model by GridSearchCV, achieved the accuracy of 0.986 and the AUC score of 0.963
Ocular Technologies, INC Boston
Research Assistant Nov 2020 - Dec 2020
Medical image detection
Use 3 different CNN models to classify 5,856 patient X ray images (earlystopping, modelcheckpoint and reduceronplateau are used to prevent overfitting) and build a model to predict whether the patient has pneumonia.
YOLO and google co-lab was used to classify 6000 ophthalmic medical images and the eye, pupil, front slit and back slit in the images were labeled.
HYDE PARK INVESTMENT SERVICES NY
Data Analyst, Private Equity Jul 2019 - Aug 2019
Investment analysis: conducted a quantitative analysis and analysis of the financial statements of SS&C Technologies Holdings inc from 2014 to 2019, summarized the overview of the cost trend, and performed an initial valuation analysis on it
Qualitative: analysis of PTC Inc’s products, operations, market position, market share, industry trends, competitor etc.
Deal execution: supporting due diligence of potential investment opportunities, financial modeling including full 3-statement LBO modeling with multiple debt and operational scenarios
TIGRESS FINANCIAL PARTNERS,LLC NY
Analyst, Equity Research Department May 2019 - Jul 2019
Conducted research on Lululemon, Target and Alcoa's income statement, balance sheet and cash flow statement, constructed trading models and evaluated the stocks of these companies
Assisted to conduct business loan due diligence and credit reviews for 4 companies
Built financial models and industry databases for Alibaba, Amazon, JD.com and Priceline
Financial modeling: input data into proprietary financial models to create charts, dashboards and supporting material
Compiled and analyzed macroeconomic, data and financial of online retail industry in China and the United States
Participated in BNY Mellon’s INSITE conference to gain an in depth understanding the trends of financial industry and covered companies
PROJECTS
Emergency Facilities Readiness Oct 2019 - Nov 2019
Focus on five hospitals in the Boston area and test how victims will be distributed to the hospitals in the event of a disaster
Based on the different capabilities of these five hospitals, performing 5,000 simulations derived the expected damage for each hospital
Under hypothetical conditions, calculated the average number of expected victims per hospital and the average total time required to transport all victims through simulation technology
Prediction and analysis of new coronavirus data Jan 2020 – Feb 2020
Used exponential smoothing, ARIMA, holtewinter and logistic regression to predict the number of confirmed, recovered and dead in Hubei Province from February 11 to February 19 .
Utilized k-means clustering to cluster patient data and compare its distribution in different locations
Predicted the result of marketing campaigns for banking institutions Sep 2019 – Oct 2019
Implemented feature engineering for data preparation, visualized correlation using heatmap and Cramer V statistics
Developed the stored procedures, queries and triggers for checking data via MySQL to store and manage over 45212 records data
Built 3 models to predict the results of marketing campaigns and test,adjust the accuracy of the models.
Through cluster analysis and prediction results to help banks find out the target customer groups
SKILLS
Programming: SAS,R Shinny,Snowflake,Python (sklearn, pandas, numpy, seaborn), R, SQL, Java, JavaScript, Scala, C,HTML,CSS.
Analytical Skills: Classical & Penalized Regression Methods, Decision Tree, Hypothesis Testing, Text Mining, Time Analysis, Regularization, Feature Engineering, A/B Testing, Supervised and Unsupervised Learning, Natural Language Processing, Tableau
Database/Big Data Engineering: MySQL, NoSQL database (MongoDB), MapReduce, Spark
Language Skills :Native in Mandarin, Proficient in English