Leo (Miao) You

Leo (Miao) You

Senior Data Scientist

Circle K

About me

Leo (Miao) You currently an Senior Data Scientist at Circle K. Prior to Circle K, he’s been working as a data analyst for over 5 years at Center for Vein Restoration - the nation’s largest physician owned vein clinic treating varicose veins and venous insufficiency.

As a graduate from University of Maryland in Marketing Analytics and Harrisburg University of Science and Technology in Analytics, Leo (Miao) You’s professional passion are data analysis and visualization, statistical modelling, data science and machine learning. As a highly motivated Data Scientist, Leo has 6+ years experience in Data Analysis and Machine Learning, 4+ years experience in Marketing Analysis and 1+ year experience in pricing optimization and data-driven merchandising

Technical Skills

  • Programming: R, Python, SAS, VBA, PowerShell, HTML, Spark
  • Database: SQL/T-SQL, NoSQL, MS SQL Server, Oracle, MySQL, PostgreSQL, MongoDB, Databricks
  • Cloud Computing: MS Azure
  • BI Tools: Tableau, Power BI
  • Data Science & Machine Learning: EDA, ETL, SSIS, General Linear (Linear/Logistics/Polynomial Regression with Regularization), SVM, Bayes, Tree-Based (Decision Tree with pruning, Random Forest, Boosted, etc.), K-NN, Clustering (K-MEANS, DBSCAN, Hierarchical), Hypothesis Testing, SSRS, Advanced Excel (Formulars, Pivot, VBA, Power Query), etc.
  • Statistical Methods: Linear and Linearizable Regression models, Generalized Linear models: Poisson and Binary models, Choice modeling using Multinomial logit, Segmentation, Targeting and Positioning using Mixture Cluster and Mixture Regression Models, Conjoint Analysis, A/B Testing, Market Demand Forecasting using Bass, Exponential and Trial-Repeat Models
  • Web and Social Media: Google Analytics, Facebook Business Manager
  • Marketing Research: Survey Monkey, Qualtrics
  • Project Management & Version Control: Agile, Scrum, TFS, Git, Airflow, Docker, Confulence
  • Others: Microsoft Office, Sharepoint

Interests

  • Data Science
  • Machine Learning
  • Data Visualization
  • Statistical Modelling
  • Marketing Analytics

Education

  • MS in Marketing Analytics, 2015

    University of Maryland

  • MS in Analytics, 2017

    Harrisburg University of Science and Technology

  • BE in Automotive Engineering, 2010

    Shanghai Normal University

Skills

R

Experienced

SQL Server

Experienced

Python

Intermediate

Statistical Modelling

Experienced

Microsoft Suite

Experienced

Data Visualization

Experienced

HTML

Basic

Machine Learning

Intermediate

SAS

Basic

Experience

 
 
 
 
 

Senior Data Scientist

Circle K

Oct 2021 – Present Tempe, AZ, 85282
Responsibilities include:

  • Led a team of 4 data scientists in developing non-linear optimization model with complex objective function and constraints in R using NLOPTR framework to provide price recommendations to business units
  • Implemented localized pricing initiatives on 9 business units with over 3000+ stores and 20k+ items from data preparation, elasticity modeling, price optimization to recommend optimal price to key stakeholders, generating 1.2M+ annual margin uplift per business unit
  • Built site selection tools using advanced ML models (Regularization, Tree-Based, XGBoost, etc.) based on 30+ features, automated model selection from 15+ models using Databricks AutoML, increasing model performance by 15% while reducing labor hour by 70%
  • Designed automated ETL pipelines using PySpark and Databricks delta tables to extract millions rows of data from multiple sources and transaction logs
  • Modularized and scaled up legacy code in Python by encapsulating codes into classes and functions, reduced average runtime by 80%
  • Served as SME and code owner in optimization models to support 20+ data scientists during the price refresh, mentoring onboarding data scientists to quickly pick up tools, platforms and data science projects by holding multiple knowledge transfer sessions.
 
 
 
 
 

Data Analyst

Center for Vein Restoration

Jan 2016 – Oct 2021 Greenbelt, MD, 20770
Responsibilities include:

  • Worked closely with IT, Operation, Sales and Finance departments and took a lead role in providing Data Reporting and Analysis
  • Approached pro-actively in the creation and delivery of reports and dashboards for problem solving and decision making
  • Performed ETL process through SQL queries and automated jobs using SQL agent that reads/writes to/from relational database and securely transfer to/from the external vendor such as Signature Forum, Xamplifer etc. using IP switch
  • Created SSRS reports, wrote MDX queries to generate OLAP cube reports and enable team to gain insights on various aspect of business such as patient cancellation and insurance billing collection
  • Identified areas where operational efficiency can be improved through automated jobs using SQL Store Procedures and views
  • Conducted root cause analysis on data discrepancies and technical issues on CRM platform and patient EHR system
  • Visualized survey results for over 200 physicians in R Studio using ggplot2, plotly and leaflet, analyzed Likert scale questions using Proportional Odds Regression model in R to identify key factors in driving referral business, presented the results in Rmarkdown format
  • Built functional Logistic regression model in R Studio to identify four significant predictors that impact appointment booking rate, improved model accuracy from 89% to 95% by using techniques such as Stepwise Selection and Grid Search
  • Used Sci-Kit Learn in Python to identify two acquisition sites that brought in over 500 new patients first year and 1.5 million in revenue by developing K Means clustering and Decision Tree algorithms, predicted potential patient volumes within 95% confidence interval
  • Designed interactive dashboard to track daily outbound recovery progress in Power BI using multi-dimensional model and DAX functions and improved outbound recovery rate by 20%
  • Prepared trend analysis reports to identify underperforming centers and deliver suggestion for tactical planning
  • Built variable commission programs for sales liaisons that optimize cost per unit and distributed utilized Excel VBA/Macro
 
 
 
 
 

Marketing Analyst

Envision Experience

Sep 2015 – Jan 2016 Vienna, VA, 22182
Responsibilities include:

  • Worked with product marketing team in creation and maintenance of reports and dashboards including marketing campaign results, web analytics, business revenue reports and teacher nominations
  • Updated Student and Mentor Program Mailing Dashboard by tracking campaign KPIs from multiple sources
  • Prepared and shared results and actionable insights to executives and key stakeholders in weekly meetings
  • Served as a liaison between external vendors such as Mercury and Marketo on data inquiries and format
  • Analyzed A/B test results to evaluate effectiveness of campaigns and websites to drive more enrollments and traffics
  • Oversee the dataflow through various of websites, including web acquisition and usage in Google Analytics
  • Assisted digital market team in monitoring Digital spend and other key metrics in Facebook Business Manager
 
 
 
 
 

Sales Analyst

Infiniti (Nissan) China

Nov 2013 – May 2014 Shanghai, China
Responsibilities include:

  • Worked collaboratively with four regional managers to conduct sales and marketing analysis of Infiniti Business Unit-China within East Regional Office
  • Collected data, prepared weekly sales reports and performance charts to present to a group of four regional managers in weekly review meetings with recommendations on strategies to enhance sales
  • Updated KPI weekly reports to the HQs, consolidated monthly KPI data to help track sales activities
  • Supervised 26 dealers’ monthly achievement rate and urged them to achieve or surpass original sales goals, resulting in 100% achievement rate in six consecutive months
  • Analyzed market share data of more than 15 competitors monthly and made recommendations to regional managers on ways to penetrate market
  • Contributed to weekly team meeting by documenting key discussion points and action items
  • Increase working efficiency by 15% after renewing car model stock report
  • Assisted marketing department in drafting quarterly marketing operation plan in terms of estimated showroom traffic, online and off-line activities

Accomplish­ments

Microsoft Technology Associate: Database Certification

Google Analytics Individual Qualification

SAS Certified Base Programmer for SAS 9

Projects

*

2019 Airbnb NYC availability prediction

2019 Airbnb NYC availability prediction using linear regression and random forest

Campus Recruitment Analysis

Campus Recruitment Data Classification and Regression Analysis

Contact Rate Analysis

CVR Contact Rate Analysis

Country Profiling using PCA and Custering

Country Profiling based socio-economic and health factors using PCA and Clustering

COVID-19 Tracker

US COVID-19 Tracker App

Crime Data Analysis

Analysis on Violent/Non-Violent Crimes in USA

Fake News Classification

Build a classifier to identify fake news from real news

Fitbit Data Visualization

Data Visualization using health data from fitbit

Patient Demographic Analysis

EDA and Logistic Regression on demographic factors influence patient appointment booking

Physician Survey

CVR Physician Survey Analysis

US Accident Data Analysis

Data Visualization and Regression Analysis on US Accident data

Contact

  • 1130 W Warner Rd, Tempe, AZ 85284