Data Computer Science

TAI NGUYEN

San Francisco Bay Area

Phone: 510-***-****/ *********@*****.*** / LinkedIn Profile / Github SUMMARY

I am data scientist with academic studies in statistical modeling, machine learning, natural language processing and deep learning. Beyond the ability of creating data models for supervised and unsupervised predictions in small scale, I am able to develop a complex big data engineering architecture on AWS cloud platform as a preparation for core machine learning and neural network algorithms. Moreover, I am a passionate innovator with keen data insights and advanced in data exploration skills.

Core Qualifications

Skills:

Statistics:

• Python, Sckit-learn, Tableau, D3, Statistics.

• TensorFlow, Keras, AWS, Google Cloud Platform.

• Spark, NoSQL, Flask, Virtual Machine, Unix.

• NLTK, TextBlob, Spacy, RegEx.

• Cleaning and exploring unstructured data for statistical relationships in Python.

• Insightful ability to preen valuable business information and engaging stories from data. Machine Learning:

Data Engineering:

• Modularizing production code for future systems and other use cases.

• Applying creative preprocessing techniques to unscaled feature data.

• Ensemble Data Modeling.

• Artful explanations of data through Python visualizations and written reports.

• Streaming API architectures & data lake procurement.

• AWS big data deployment and management. RDS SQL developer & administrator. Natural Language

Processing:

Deep Learning:

• Develop effective Regex techniques to extract complicated contextual data.

• Applied preprocessing techniques for unstructured features, such as WordNet and PCA.

• Semantic text visualization and insights through a spectrum of word2vec, bigram, topic modeling.

• Vectorizing and Ensembling imbalanced datasets with potential optimizers, such as K-fold cross validation.

• Building a Tensorflow MLP with Gradient Descent Optimizer and back propagation features.

• Developing a Keras model to train an image dataset by a Convolutional Neural Network and sentiment text dataset by Long Short Term Memory Neural Network over Google Cloud Platform. ACADEMIC QUALIFICATIONS:

12/2017 Master of Science: Data Science - University of New Haven (San Francisco) 08/2016 Bachelor of Science: Computer Science (Major)/ Mathematics (Minor) San Francisco State University

COMPUTER & DATA SCIENCE EXPERIENCE:

08/2017 – 12/2017 Business Intelligence and Big Data Mining (Verisk Analytics) Creative applications in big data mining and analytics including extracting data sources for energy disasters and database development of unstructured data for insurance underwriting and business intelligence systems.

2016 Developing a POST (Point of sale terminal) system Agile team development of a POST system for receiving a transaction file, including multi-line records, that programmatically provide a printed invoice. With a database to record business products, the system architecture is based on a model-view-controller (MVC) pattern. 2015 - 2016 Developing front end for an online shop website Development of an online Front-End system that enables customers to buy and sell items in a local geographic neighborhood. Use case tasks include:

+ GUI design and testing based on UX, and SW design principles.

+ Test driven development to fix formatting errors occurring at the front end.

Contact this candidate