Data Scientist Machine Learning

Siyu (Coco) Chen

484-***-**** ************@*******.*** LinkedIn

OBJECTIVE

Aspiring Data Professional with expertise in Python, SQL, and data visualization tools. Skilled at transforming complex data into actionable insights to drive strategic business decisions through cross-department collaboration. EDUCATION

Carnegie Mellon University, Pittsburgh, PA August 2023 – December 2024 Master of Information Systems Management

Courses: SQL Database Management, Agile Methods, Machine Learning in Production, Generative AI Lab, Marketing Analytics Lehigh University, Bethlehem, PA August 2019 – May 2023 Bachelor of Science in Computer Science, High Honors Minor: Data Science SKILLS

Programming: Python (Scikit-learn, Keras, Plotly, SciPy, NumPy, Pandas), R, SQL, PyTorch, TensorFlow, Java, HTML, Excel, Git Big Data: Databricks, Hadoop, Kafka, MapReduce, Azure, Spark, AWS, Snowflake, Tableau, PowerBI, NLP, Airflow, Docker Statistics and ML: GLM, k-NN, SVM, GBM, Naive Bayes, k-Means clustering, PCA, A/B Testing, Causal Inference PROFESSIONAL EXPERIENCE

Data Scientist Intern, DealMate, Pittsburgh, PA June 2024 – August 2024

● Designed and implemented enterprise-wide database systems using SQL, streamlining accessibility for cross-functional teams

● Developed a Voiceflow chatbot that elevated user engagement by 30%, supporting bookings and delivering real estate insights

● Defined performance metrics in collaboration with engineering and data teams, ensuring alignment of chatbot functionality with the product roadmap

● Built a collaborative filtering recommendation system (k-NN) to deliver personalized user suggestions

● Conducted A/B testing on chatbot dialogue flows, optimizing engagement and improving conversion rates by 25% Data Scientist Intern, Xiamen Airlines, Xiamen June 2023 – August 2023

● Saved fuel costs by 15%, through feature engineering and predictive modeling with large number of flight records using XGBoost

● Applied Multivariate Linear Regression and Ridge Regression to analyze key operational variables (altitude, speed, payload weight), uncovering optimizations that boosted fuel efficiency by 15% per flight segment, resulting in notable cost savings

● Enhanced ETL workflows by restructuring SQL queries and implementing parallel processing, increasing data accessibility and speeding up decision-making across departments through faster pipeline performance

● Delivered insights through dynamic Tableau dashboards, empowering stakeholders to make data-driven decisions on flight operations and logistics

Program Manager Intern, Jabra Corporation, Xiamen June 2021 – August 2021

● Revamped departmental intranet with SharePoint and JavaScript, reducing support cost by 25% and increasing workflow efficiency

● Conducted user analysis and feedback sessions, leading to a workflow redesign that reduced internal ticket volume by 20% and improved project management processes

PROJECTS

Movie Recommendation System, Carnegie Mellon University August 2024 – December 2024

● Built and deployed an Item-Based Collaborative Filtering model to deliver personalized movie recommendations, processing user requests to refine recommendation accuracy

● Performed load testing and scaled API services using Flask and Kafka, achieving 99.9% uptime and reducing latency by 40%

● Deployed real-time monitoring system using Prometheus and Grafana to analyze KPIs including user engagement and retention

Gen AI Lab Projects, Carnegie Mellon University March 2024 – May 2024

● Built RAG pipelines to improve search relevance for text-heavy datasets, integrating embeddings and chunking strategies to improve retrieval accuracy by 35%

Customized Search Engine for AEquitas, Lehigh University January 2022 – December 2022

● Architected a bespoke search engine for AEquitas, a non-profit legal organization, employing Elasticsearch, AWS Lambda, S3, and EC2 instances, integrated via RESTful APIs for scalable and efficient query processing

● Trained a word2vec model to embed Conceptual Search capabilities, strengthening search functionality and optimizing the Solr configuration for more nuanced and context-aware results LEADERSHIP

Computing Services Consultant, Heinz College Computing Services, Carnegie Mellon University August 2024 – December 2024 Student Ambassador, Heinz College Ambassadors, Carnegie Mellon University December 2023 – December 2024

Contact this candidate