Kunbo Zhang

New York, NY 929-***-**** ad17df@r.postjobfree.com LinkedIn

EDUCATION

Columbia University, Graduate School of Arts and Sciences New York City, NY MA in Statistics 09/2022 - Exp 05/2024

● Coursework: Machine Learning, A/B Testing, Deep Learning, Big Data, Database Design, Cloud Computing University of California, Santa Barbara, College of Letters and Science Santa Barbara, CA BS in Statistics and Data Science 09/2019-07/2022

● Coursework: Probability, Advanced SQL, Database System, Causal Inference, Design of Experiment WORK EXPERIENCES

Kuaishou Technology Co., Ltd. Beijing, China

Data Science & Analytics Intern, Live Streaming Strategy Department 07/2023-09/2023

● Utilized SQL to calculate and optimize live streaming KPI metrics such as CTR, CVR, ARPU, and ROI; exercised adept communication by presenting nuanced, data-driven business insights to stakeholders through slides

● Performed opportunity sizing and headroom analysis, pinpointing high potential and underperforming live streamers by a funnel metrics framework; collaborated with PMs to enhance user engagement

● Conducted A/B Test to adjust the feed impression distribution for low performance live streamers and validate the key revenue indicator for low performance streamers (follower-driven); improved more valuable traffic to high-potential streamers and increased 5% rise in regional monthly live streaming revenue

● Performed deep dive analysis to explore the relationship between live streaming durations and revenue, summarized key insights about key factors (CVR) on how to improve live streamers’ revenue

● Built 10+ data pipelines to process raw data from upstream tables in the Hive data warehouse and track live steamer’s information through different categories (game, sports, education etc..) Nanjing Yucan Information Technology Co., Ltd. Nanjing, China Data Analyst Intern, Informatization Development Group 06/2021-08/2021

● Designed and optimized key product metrics including DAU, session duration, and queries per location to evaluate map

& navigation products’ user experience performance

● Conducted deep dive analysis to identify the root causes of map KPIs fluctuations such as feature changes and data integrity issues; compiled analytical framework to cross functional team members’ use

● Built 5 ETL pipelines to generate monthly and weekly data reports; streamlined data updated process by 2 hr/per week

● Leveraged Tableau to connect with internal database and built interactive OLAP Dashboards to visualize map user experience KPIs and track short-term and long-term trends Beijing Zhuochu EDU Technology Co., Ltd. Beijing, China Data Analyst Intern, Data Analysis & Operations Department 03/2021-06/2021

● Executed SQL queries to extract 20k data outputs to obtain granular insights into user behavior, preferences, and engagement patterns of the online education platform

● Applied advanced Excel techniques including VLOOKUP and Pivot Tables for data integration and summarization

● Targeted on 10k new customers to perform funnel analysis to identify potential opportunities to improve conversion rate on different stages of users first online course sign up process

● Performed in-depth Exploratory Data Analysis to unveil patterns in user data, and utilized feature importance analysis to prioritize impactful engagement factors; informed strategic retention initiatives that reduced customer churn by 25%, bridging data analysis with actionable business outcomes PROJECT EXPERIENCES

Predicting Match Outcomes in Speed Dating Spring 2023

● Built match prediction model for speed dating using logistic regression, SVM, decision tree, and XGBoost

● Performed recursive feature selection and hyperparameter tuning; achieved highest accuracy of 0.918 with XGBoost Movie Recommendation System Spring 2023

● Built a movie recommendation system using PySpark for 45k movies, 26M ratings, and 270k users

● Employed ALS algorithm for collaborative filtering that minimized MAE to 0.7

● Leveraged TF-IDF approach to convert movie features into relevance scores and implemented a content-based filtering model; built a hybrid recommendation system for personalized movie suggestions based on user preferences & behavior SKILLS

● Programming Languages: SQL, Python(Pandas and Numpy, Sklearn and Pytorch, Pyspark, Flask), R, SAS

● Big Data: Hive, Spark, Kafka(message queue), AWS (S3, Sagemaker, DynamoDB, Redshift, Lambda, Opensearch)

● Analytics Techniques: A/B Testing, Clustering, Data Visualization(Tableau), ETL Pipelines, Data Mining

Contact this candidate