Sign in

Data Analyst, Data Scientist, Python, SQL, Machine Learning

Syracuse, NY
November 29, 2020

Contact this candidate


Dan Li



Syracuse University – College of Engineering & Computer Science, Syracuse, NY Master of Science in Computer Science, GPA: 3.9/4.0 Jan 2019 – Dec 2020 Syracuse University – College of Art & Science, Syracuse, NY Doctor of Philosophy in Biology Aug 2012 – Aug 2018 China Agricultural University – College of Food Science and Nutritional Engineering, Beijing, China Bachelor of Engineering in Viticulture and Enology Aug 2007 – Aug 2011 TECHNICAL SKILLS

§ Programming Languages: Python, C++/C, JavaScript, HTML, CSS, SQL, R

§ Tools: Tableau, Jupyter Notebook, Google Analytics, Git PROJECT EXPERIENCE

Improve Read Write Performance for LevelDB Sept 2020 – Nov 2020 Group Project – Group Member

§ Benchmarked and analyzed the database’s performance with different system parameters

§ Incorporated read-write locks to the database and achieved performance gain in both read and write operations

§ Implemented an off-line cache updating policy and optimized the database’s write performance for time-series data

Blink Detection and Blink Controlled Game Oct 2020 – Nov 2020 Individual Project – Independent Contributor

§ Constructed a blink detection system that used the front camera of a laptop to identify and track the user’s blink status

§ Added decay factor in blink detection model and improved blink detection accuracy by 12%

§ Integrated the blink detection module into game Dino-run, enabled blink-triggered jump over obstacles Sentiment Analysis of US Airlines Using Tweets Mar 2020 – May 2020 Group Project – Group Leader

§ Led a 4-member team and formalized the project aims and milestones

§ Monitored project progress on a weekly basis to reinforce timely communication, collaboration, and delivery of results within the team

§ Measured customers’ sentiment towards different airlines using tweets, analyzed the factors that contributed to the satisfactory levels for airline services, and developed models that automatically extract tweet text and correlate customers’ concerns

§ Created data visualization and presented final project findings to a class of 50 students Building Flavor Wheels for Different Wine Varieties from Tasting Reviews Oct 2019 – Jan 2020 Individual Project – Independent Contributor

§ Imported, cleaned, and preprocessed publicly available wine reviews utilizing pandas/numpy framework, crawled and tidied additional 50k reviews for testing and referencing

§ Computed words best describe the top characteristics of different wine varieties. Built master flavor wheel for all wines and stemmed individual ‘cheat sheet’ flavor wheel for 30 major wine varieties

§ Taught a class of 20 students with usage of these ‘cheat sheet’ to perform blind wine tasting and received 34% improvement on students’ classification accuracy

§ Built and analyzed supervised and unsupervised models with scikit-learn to automatically deduce wine varieties from tasting reviews and achieved 84% accuracy with 30 major varieties PUBLICATION

JMJ14 encoded H3K4 demethylase modulates immune responses by regulating defence gene expression and pipecolic acid levels (Li, Dan, et al. New Phytologist 2020)

Contact this candidate