Jinyu Xu
Product Data Scientist @Meituan
Signup · Get unlimited contacts
WORK HISTORY
Product Data Scientist @Meituan
Beijing, CN
Feature Engineering: Tackled 6k+ missing data by imputation with mean, down-sampling for imbalanced data; implemented PCA and ANOVA to extract 8 features from 46 variables with 99% variance contribution ·Machine Learning: Utilized Random Forest and XGBoost model in Python to forecast courier demand, metrics: shop & consumer density, weekdays, peak hours; visualized results on PowerBI, increased lunchtime on-time rate by 12% ·A/B Testing: Designed controlled experiment with R using a T-test to estimate the impact of expanding the bicycle\'s delivery range, reduced the average postage per order by HK$0.56, improved on-time rate for 0 to 500 meters by 10% ·Correlation Analysis: Investigated correlation between supply-demand ratio and courier rejection rate via Pearson Correlation Coefficient; located the experience deterioration threshold, finally increased the courier on-time rate by 8% ·Root Cause Analysis: Analyzed reasons for cyclists\' overtime from supply-demand ratio, pickup distance, ETA, and ATA, etc. by Five Whys Method and Fishbone Diagram, innovated 5+ strategies and reduced the cyclist overtime rate by 14%
EDUCATION
The Chinese University of Hong Kong, Shenzhen 香港中文大学（深圳）
Bachelor of Science - BS, Statistics
Columbia University
Master of Science - MS, Operations Research
ABOUT JINYU XU
I am a skilled and self-driven Data Analyst, and I am experienced working in the diverse domains of business, such as technology, logistics, manufacture, and real estate. I tend to look at every problem with an analytical and critical attitude. I am adept at innovating solutions using Python, SQL, and R. Communication is the strong thread that holds all the pieces together and thus I take it seriously. I invest heavily in interpersonal relationships whether it is with key-stakeholders, clients, or the management because none of us can work in isolation. Ultimately it’s a collaboration that wins. I am looking for internships where I can learn more about Data Science, Analytics and apply all that I’ve learned so far. Technical Skills: Python | SQL | R | PySpark | Hadoop | Advanced Excel | Tableau | PowerBI | FineReport | C++| JavaScript | MS-PowerPoint | MATLAB Soft Skills: Strong Analytical Thinking| Leadership Skills| Decision Making| Team Player| Effective Negotiator| Persuasive Communicating| Multi-Tasker | Customer Relationship Management | Self-motivated Relevant coursework: Python Programming (Pandas, NumPy, Scikit-Learn, Tensorflow)| R (ggplot2, dplyr, caret)| SQL (MySQL, HANA, ClickHouse)| Business Data Warehousing| Statistics for Data Analysis| Predictive Analytics using SAS| Data Visualization| Applied Machine Learning| Business Analytics Areas of Interest: Data Science | Data Analytics | Data Engineering | Business Analytics| Data Visualization | Business Data Warehousing | Data Mining It would be great to hear from you, I can be contacted through; Email - j•••••@columbia.edu or, feel free to drop me a message over Linkedin.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.