Clement Chen Email & Phone Number

New York, NY, US

New York City Metropolitan Area

New York City Metropolitan Area

• 550+ hours of hands-on course material, with 1:1 industry expert mentoroversight, and completion of 2 in-depth capstone projects. Mastered skills in Python,SQL, data analysis, data visualization, hypothesis testing.
• Preprocessed image data using zero-padding and data augmentation to prevent feature distortion and overfitting.
• Constructed a CNN image recognition model utilizing the convolutional base of the pretrained VGG16 network.
• Implemented GPU parallel processing in TensorFlow to accelerate hyperparameter tuning under a Bayesian Optimization metric by 4 times.Wine Quality Modeling
• Analyzed 5000 red and white wine samples using physiochemical properties to model wine quality in SKlearn.
• Trained multiple machine learning algorithms such as Logistic Regression, Gradient Boosted Trees, and Random Forest optimizing each using 5-fold CV hyperparameter tuning.

Syracuse, New York, United States

• Collaborated with colleagues from the Masters Program and the Data Science team at The City of Syracuse to use rental data to classify properties prone to health hazards such as lead paint
• Used Jupyter Notebook and Google Collab to ensure code was organized and consistent between members
• Explored external data sources such as the Zillow Group API and webscraping rental listings from sites such as Apartments.com and Rentals.com to cross verify and supplement the raw data
• Utilized Natural Language Processing (NLP) libraries and String Matching algorithms along with domainknowledge to feature engineer data essential for a complete analysis
• Trained a machine learning classification model to identify properties prone to health hazards using LogisticRegression and Random Forest Classifiers with 95% + test accuracies
• Outlined a strategy to develop an optimized pathing route inspectors could employ to prioritize properties that were likely to have a health violation and within close proximity to each other

Binghamton, New York, United States

• Worked with colleagues from the MS Program and the Data Science team at Visions to assess pandemic impact on physical/online banking channel usage trends
• Performed exploratory data analysis and cleansing on banking data to identify and correct inconsistencies
• Built a cross-sectional dataset by integrating Google Mobility Reports and Covid-19 daily cases data
• Developed and visualized predictive time series models using the Prophet and Plotly Python libraries to forecast post-pandemic recovery trends

Vestal, New York, United States

• Worked with graduate students in Professor Bonggu Shim’s non-linear optics research group on experiments such as 3D characterization of index profile of a waveguide using interferometric tomography.
• Learned about different data acquisition methods, automated image data collection using arduino, and data analysis techniques using fourier methods implemented predominantly in Python
• Contacted companies about purchasing specialized materials and for equipment repair
• Mentored undergraduates new to the group by training them on proper laser safety procedures
• Participated in weekly group meetings where members presented academic papers to stay informed on advancements in the field of non-linear optics

Master Of Science - Ms, Data Analytics, 3.68

Bachelor Of Science - Bs, Theoretical And Mathematical Physics, 3.75