Data Analyst Sales

Xin(Tracy) Cui

San Diego, California +1-909-***-**** ****@****.*** Green Card Holder

Education

University of California, San Diego Aug 2019-Dec 2021 Master of Science in Business Analytics

Courses: Neural Networks for Pattern Recognition; Statistical Natural Language Processing Guangzhou University - Guangzhou, China July 2013-July 2017 Bachelor of Science in Accounting, GPA: 3.5

Work Experiences

Mercedes-Benz, Guangzhou, China Oct 2017-Feb 2019

Data Analyst on Recommendation System and Customer Retention

• Built Content-based Filtering and Collaborative Recommendation using TF-IDF and Scikit-Surprise to recommend cars to the customers, which promoted to target customers more effectively and efficiently via the digital advertising. The recommender system increased the click-through rate by 10% and proportion of orders with recommendations by 13%.

• Extracted and integrated customer data from multiple sources using SQL and created a Tableau dashboard for the Sales and Marketing team and developed presentation about a full view of customers’ purchase behaviors and preference

• Analyzed the data of retained and churned customers with Matplotlib and Seaborn, and implemented Random Forest Classifier to predict the likelihood of a custmer to stay with Mercedes-Benz, which helped increase the retention by 15%. Uber, Guangzhou, China Feb 2016-Jun 2016

Data Analyst Intern on A/B Testing and Demand Prediction

• Predicted the rider demand with the Time Series RNN Model(LSTM) with Keras, which brought more efficient driver allocation which has decreased waiting time by 3-5 minutes on average for the riders.

• Worked closly with product manager and conducted advanced A/B Testings with Uber’s Experimentation Platform to improve the users’ satisfaction. Monitored the impact of the features on the key metrics with the R shiny dash broad, completed the post experiment analysis using Chi-Square Test, T Test, etc, and developed presentation about the analysis to the product team.

• Retrieved and pre-processed large scale data from data sources Hadoop ecosystem using Hive. Teradata, San Diego, California Jun 2019-Aug 2019

Data Analyst Intern on Renewal and Sales Performance

• Cleaned and categorized 10GB data of renewal and sales with Python(Pandas, Regular Expressions, SciPy, Matplotlib)

• Analyzed the data from all the renewal and sales with Linear Regression and Logistic Regression, and created dashboards to visualize the insights of the growth of ARR to the renewal team via MySQL, dplyr and ggplot2.

• Reviewed contracts and purchase orders for potential revenue recognition issues to determine appropriate recognition of revenue.

Selected Projects

Natural Language Processing & K-Means Clustering: Apr 2020 – Jul 2020 Clustering coronavirus global news to helps users keep up with the ongoing pandemic issues and search the specific topics

• Processed the text from the body of 50,000 news using Natural Language Processing (NLP).

• Used Principal Component Analysis (PCA) to project down the dimensions of data and used t-SNE to reduce dimensionality in order to visualize clusters of instances in high-dimensional space.

• Applied k-means clustering on data and applied Topic Modeling using Latent Dirichlet Allocation (LDA) to discover keywords from each cluster.

• Investigated the clusters with classification using Stochastic Gradient Descent (SGD). Skill Set

• Programming: SQL, R(tidyverse, dplyr, ggplot2, shiny), Python(Scikit-learn, Tensorflow, Matplotlib, Seaborn), Spark(Scala, PySpark), Hadoop

• Analysis & Modeling: A/B Testing, Machine learning(Regression, Neural Networks, Tree Based Methods)

• Analysis Visualization Tools: Tableau, Power BI, Advanced Excel

Contact this candidate