Post Job Free

Resume

Sign in

Data Analyst Science

Location:
Pittsburgh, PA
Posted:
August 22, 2023

Contact this candidate

Resume:

Yiluo Qin Phone number: 909-***-****

Email: ady46x@r.postjobfree.com

Github: github.com/fernieq

EDUCATION

Carnegie Mellon University, Pittsburgh, PA Master of Science in Electrical and Computer Engineering Cumulative GPA: 3.6/4.0 Feb 2021 — May 2023

University of California San Diego, San Diego, CA Bachelor of Science in Data Science Cumulative GPA: 3.6/4.0 Major GPA: 3.8/4.0 Aug 2016 — Jul 2020 SKILLS

Programming Languages: Python, Java, SQL, JavaScript, R, HTML, and Matlab Software/Frameworks: PowerBI, Tableau, Snowflake, TensorFlow, Spring Boot, Next.js, PySpark, Airflow and SageMaker Knowledge: Machine Learning, Deep Learning, Reinforcement Learning, Hypothesis Testing, Data Engineering, Data Visualization, Relational Database Management, NoSQL, and Applied Probability and Statistics WORK/RESEARCH EXPERIENCES

Data Analyst at Computing Services Center at CMU Pittsburgh, PA, Feb 2023 — Present

• Facilitated the data migration to Snowflake and ensured the integrity of the ingestion pipeline for future usage.

• Recreated various expenditure datasets from the Alteryx workflow by creating views and tables in Snowflake.

• Utilized Tableau to create detailed dashboards reflecting the KPIs suggested by the school executive board. Data Science Intern at Dell Pittsburgh, PA, Jun 2022 — Aug 2022

• Performed Dell telemetry data preprocessing, standardization, feature engineering, and filtering with Python and SQL.

• Designed Decision Tree baseline line model with pruning to reach a balanced accuracy score of 54%.

• Optimized supervised learning models with feature selections and a stacking classifier with a balanced accuracy score of 62%.

• Modeled K Means Clustering unsupervised learning model and reached a 89% on the binary pre-labeled data. Research Assistant on TikTok User Behavior Research at CMU MINT Lab Pittsburgh, PA, Nov 2020 — Feb 2022

• Performed quantitative data analysis to test and verify how user understandings of algorithms influence content creation.

• Discovered features including video creation time and video engagement highly positively correlated with video play count.

• Found out simply stacking up trending hashtags could negatively affect video popularity in terms of play count. Research Assistant on Summer Sleep Study Research at CMU Pittsburgh, PA, Jun 2021 — Sep 2021

• Performed SMOTE and under sampling techniques on five distinct classes to tackle dataset imbalance on the server.

• Co-developed one CNN model and classified kids’ five sleeping stages using EEG channel with a 60% accuracy. Data Science Intern at TeraData San Diego, CA, Jul 2019 — Sep 2019

• Helped to clean up and reconstruct multiple health care datasets using Pandas and SQL.

• Assisted to build one prediction model with SageMaker and TensorFlow for a local pharmaceutical company. Data Analyst Intern at Microsoft Shanghai, China, Jun 2018 — Sep 2018

• Accomplished data preprocessing and cleaning of electricity consumption data in Shanghai and Beijing campus with MySQL.

• Composed an interactive electricity consumption comparison dashboard for Shanghai and Beijing campus with PowerBI. PROJECTS

Promptopia Pittsburgh, PA, Aug 2023

• Built a full stack RESTful AI prompting tool accommodating the increasing reliance on AI with React Next.js framework.

• Handled various prompt requests by different users with MongoDB and authenticated correct user privilege with Nextauth.

• Implemented additional features of filtering by prompt keywords or by user, tags on-click search, and viewing profiles. Card Manager Pittsburgh, PA, Jun 2023

• Built a full stack RESTful micro service app managing debit/credit cards information with Java Spring Boot framework.

• Performed functional testing including unit testing, integration testing, and system testing throughout the development phase.

• Implemented features of user sign-up/sign-in, activate/deactivate a card, fetch card information, change daily limit on a card. Chicago Crime Rate Visualization Dashboard Pittsburgh, PA, Dec 2022

• Reconstructed and filtered online source data that have more feature completeness using SQL and Python.

• Wrote several functions in JavaScript to link different sections of the dashboard and enabled various on-click, scroll effects.

• Synchronized visualizations with HighCharts, JavaScript, HTML/CSS, and Python to display the final data. Single Person Web Blog San Diego, CA, Jun 2020

• Created a database to store, retrieve, and update users and posts’ information using SQLAlchemy.

• Utilized various Python Flask extension classes to handle different jobs such as resetting password, login, and register.

• Displayed Flask forms to display various form templates and HTML with inheritance and Bootstrap to handle web pages. Olympic Game Dataset from Kaggle San Diego, CA, Dec 2019

• Identified functional dependencies across all attributes and designed an ER Diagram to fully represent cardinalities.

• Created table statements with optimal data type declarations and populated the data with PostgreSQL.

• Decomposed resulting entities into 3rd Normal Form (3NF) and executed queries based on questions of interest. PUBLICATIONS

Trick and Please. A Mixed-Method Study on User Assumptions About the TikTok Algorithm

• Published in the Proceedings of the 13th ACM Web Science Conference 2021 (WebSci’21).



Contact this candidate