Yancheng Zhang

Email: ady466@r.postjobfree.com Tel: +1-929-***-****

EDUCATION BACKGROUND

Columbia University New York, US

M.S in Data Science, 3.93/4.0 Aug 2022 - Dec 2023

Courses: Machine Learning, Algorithms for Data Science, Natural Language Processing (Lesk Algorithm, Beam Decoder, Deep Learning), Computer System (SQL), Data Visualization (R), Statistical Inference and Modeling, Probability and Statistics Nankai University Tianjin, CN

B.Econ in Finance with Highest Honor, 90.29/100 Sep 2018 - Jun 2022 Courses: Econometrics, Quantitative Investment, Accounting, Corporate Finance, Real Analysis, Stochastic Calculus, Time Series Honors: Highest Honor in Graduation Thesis, Visiting Student Fellowship, Provincial Scholarship (1%), Innovation Scholarship WORKING EXPERIENCES

Warner Bros. Discovery New York, US

Data Scientist and Analytics Intern Jun 2023 - Aug 2023

Conducted a data-driven project to pinpoint key indicators of successful streaming sessions, in order to enhance customer satisfaction and engagement

Used SQL to extract data from Snowflake, applied the XGBoost algorithm on AWS to analyze 15M+ user sessions, evaluated attributes such as click actions, device categories and profile types in relation to session outcomes; improved AUC from 80% to 86%; improved PRAUC from 81% to 91%

Leveraged SHAP values in a feature importance model to identify critical user actions, enabling the development of targeted intervention strategies by product teams

Devised a method to filter out lack-intent-to-watch sessions, enabling better classification of session outcomes and facilitating targeted advertisement interventions

L'Oréal S.A. New York, US

Capstone Project - Sales Prediction with Machine Learning Feb 2023 - May 2023

Led a team to develop a sales prediction model for L'Oréal's subsidiary brand Kiehl's by implementing various time-series forecasting techniques, including ARIMA, LGBM, and Prophet, to optimize the company's cash flow management

Conducted in-depth data analysis and visualization of store traffic and sales data for Kiehl's stores in the US, identifying relationships between passby traffic, holidays, and sellout records to enhance sales prediction accuracy

Integrated external data sources, such as census data on population size and household income, to better capture the effects of geographic factors on store traffic and improve model performance Huatai Securities Co., Ltd. Shanghai, CN

Asset Management Intern Jun 2022 - Sep 2022

Built ETL pipeline from various data sources using SQL and Python and delivered data solutions to product team

Proposed three-factor model to predict stock-bond correlation based on inflation shock, economic development shock and their correlation using fixed-effect regression, analyzed transformation of asset allocation in positive stock-bond correlation condition

Executed Tableau to visualize price changes of Dollar, Gold, Brent Crude, U.S Treasury Bond, etc and divide them into leading assets and delayed assets

Wrote empirical report based on US monthly data from 01/1919-08/2022 to show real estate & PMI as prior indicators, and unemployment & CPI as delayed indicators during recession so as to argue against Waller’s opinion about soft landing Accenture Co., Ltd. Beijing, CN

Management Consulting PTA Aug 2020 - Sep 2020

Conducted market research and case studies to analyze healthcare welfare strategies of tech giants, media companies, and foundations, identifying trends like product creation, online health education, and disease eradication initiatives

Developed tailored recommendations for our client, a media company, advising on the integration of health education and online healthcare services into their platform for social impact and market expansion

Communicated data-backed insights and strategic recommendations to our client's senior management, emphasizing alignment with industry trends and the potential for brand enhancement and public health contributions CSC Financial Co., Ltd. Beijing, CN

Quantitative Research Intern Jun 2019 - Jul 2019

Assisted the development of event-driven stock trading algorithms to guide transaction decision

Leveraged SVM and random forest ML models to predict future return based on momentum alpha factors for stock selection, including alpha13, ADX, annual firm set growth rate, turnover return, bias turnover, etc.

Performed automated trading based on technical indicators and strategies, validated by backtesting on 5-year Chinese market RESEARCH EXPERIENCES

Research Assistant Columbia University, Marketing Department, Prof. Olivier Toubia Sep 2023 - Dec 2023

Narrative Topography in Success Prediction: Use Generative AI to uncover causal, interpretable factors in unstructured data

Leverage word2vec embedding method in academic/movie text scripts, measure causal effect of speed/volume/Circuitousness to its acceptance by readers / viewers

Part-time Research Assistant Harvard University, Economics Department, Prof. David Yang Aug 2021 - Present

Impact of International Investment in Africa: Investigated the correlation between international investment and democratization in African countries, try to understand how foreign investments affect political developments in the region

Corporate Migration from Shanghai to Hong Kong in the Late 1900s: Analyzing historical economic data and corporate reports to understand the driving factors behind companies relocating from Shanghai to Hong Kong in the late 1900s, try to understand the role of economic policies, market dynamics, and geopolitical factors SKILLS

Programming: Python (NumPy, SciPy, Pandas, Scikit-Learn, Matplotlib, Seaborn), SQL, R, MATLAB, Stata, LaTex AI Models: Regression (OLS, Logistic Regression, Ridge Regression, SVR), Bayesian, Supervised Classification (KNN, SVM, Random Forest, Boosting, XGB), Unsupervised Clustering (K-Means, Hierarchical Clustering), Neural Networks, Deep Learning (CNN, RNN) Big Data: Hadoop Map Reduce, Apache Spark

Data Visualization: Histograms, Frequency Polygons, Box-Plots, Quantile Plots, Scatter Plots, Alluvial Plots, Heatmaps, EDA, ROC Statistics: Statistical Inference, Hypothesis Testing, Bayes Theorem, ANOVA, Time Series (VAR, Local Projection, ARMIA, Prophet) Analytics: A/B Testing, SWOT, Maslow’s hierarchy of needs, PESTEL, KANO, Fogg Behavior Model Metrics: Finance (gross/net profit margin, operating profit, ROI, quick ratio); Marketing (eCPM, funnel analysis, conversion rate, click through rate, google analytics); Product (A/B testing, DAU/MAU Ratio, customer engagement rate, customer acquisition cost); Website

(upstream / downstream sites, unique users, number of visits, time spent, search traffic)

Contact this candidate