Chicago, IL 312-***-**** email@example.com
Enthusiastic Data Scientist with a strong mathematical, statistical, and programming foundation. Skillful at utilizing Statistical Modeling and Machine Learning techniques to drive actionable insights from data. Adept at designing and prototyping data visualization tools. CORE COMPETENCIES
Programming Languages: Python, R, SQL, Java, MATLAB, C Machine Learning: NumPy, Pandas, Scikit-learn, NLTK, Gensim, Statsmodels, Keras, TensorFlow Database and Cloud: PostgreSQL, Hadoop, MapReduce, Spark, NoSQL, Microsoft Azure Visualization Tools: Tableau, Matplotlib, Seaborn, Plotly, ggplot2, Shiny EDUCATION
MS in Data Science Aug 2018 – Dec 2019
Illinois Institute of Technology GPA 3.9 Chicago, IL, USA BS in Applied Mathematics Sep 2010 – Jun 2014
Ocean University of China Outstanding Graduate Qingdao, China EXPERIENCE
Basil Labs Data Science Internship Remote April 2020 - Present
§ Processing location information and reviews scrapped from Google Maps.
§ Building and testing Topic Modeling and Sentiment Analysis pipelines using Python.
§ Tapping into consumer perceptions of Chicago to help tourism and business recover post-COVID-19. https://www.linkedin.com/pulse/how-can-chicago-recover-tourism-post-covid-19-shengnan-li/ CCC Information Services, Inc. Data Science Practicum Chicago, Illinois, USA May 2019 – Aug 2019
§ Extracted and processed AWS information by Web Scrapping and NLP techniques.
§ Designed Tableau dashboards to visualize and report text data.
§ Built Text Similarity algorithms and a Chatbot that allowing users to get AWS EC2 recommendations.
§ Designed questionnaires to collect testing sets and achieved more than 80% accuracy. Jinan Construction Bidding Consulting Co. Ltd. Data Analyst Jinan, Shandong, China Jul 2014 – Sep 2017
§ Aggregated, cleaned, and formatted quotations of multiple companies via Microsoft Excel.
§ Constructed formulas to analyze bidding data and reported to experts for choosing the best offer. PROJECTS
Stock Returns Forecasting with Deep Learning (2019)
§ Utilized Python and Keras library to create Deep Learning pipelines and predict stock returns three months later.
§ Applied Grid Search and Cross Validation methods for hyperparameter tuning.
§ Identified the importance of various factors in predicting stock returns and reduced 30% time consumption using only critical factors to predict stock returns.
Yelp Rating Prediction and Improvement for Restaurants with NLP (2019)
§ Cleaned, processed, and filtered 6M+ reviews in Yelp via Apache Spark.
§ Identified critical factors affecting restaurant ratings using NLP technology and LDA modeling.
§ Developed a user interface via R Shiny allowing users to get rating predictions and improvement guidelines for their restaurants based on review analysis.
Time Series Analysis for Restaurants’ Stock Optimization - Group Leader, HAVI Company (2018)
§ Built a SARIMA model via Python to forecast daily sales of fast-food restaurants.
§ Optimized and visualized restaurants’ stocking approaches for different days and times of the week.
§ Avoided unnecessary restocking during restaurants’ peak sales times.