Graduate Student Resume
Dallas, TX
SUMMARY:
Master’s degree of Data Science and Software Engineering, experience with data analytic and big data modeling, skillful with machine learning, data mining, Python, R and SAS, 7 years working experience, goal oriented professional
DATA SCIENCE SKILLS:
Machine Learning algorithm: Decision Tree, Random Forest, kNN, SVM, K - means, DBSCAN, Linear Regression, Logistic Regression, PCA, LDA
Data Science P ackages: Scikit-learn, Pandas, NumPy, nltk, spaCy, pattern3, WordNet
Programming: Python, SQL, R, JSON, XML, Java, C++
Tools: SAS, MySQL, SQL Server, Oracle, MongoDB, matlibplot, Excel
RESEARCH EXPERIENCE:
Confidential, Dallas, TX
Graduate Student
Responsibilities:
- Apply unsupervised clustering machine learning method to detect BGP anomaly
- Use over 7 million of raw data records and over 20,000 statistical data records for analysis
- Detect anomaly successfully for the historical events with 0.82 silhouette score of DBSCAN
- Use supervised and unsupervised machine learning methods to train and test data of 1094 Confidential high schools and predict possibility of college enrollment rate of high schools
- Final optimized random forest model obtains 94% accuracy in probability of college enrollment prediction
- Working with streaming data: Mining Twitter Data with Python and MongoDB
- Build a sample service that accepts data from a Twitter stream and stores it locally in a MongoDB database
- Use predictive regression models in SAS on Kobe’s shot attempts dataset to predict Kobe’s shot
- Build regression models with statistical tools in SAS to predict housing prices
- Obtain 0.9215 in adjust R2 with the final model
- Conduct Topic modeling analysis for user reviews of IMDB action movies.
- Use NLP topic modeling pipeline. Text scraping, text normalization, building up NMF model with tfidf feature extraction, finding out top topics with most weighted terms
Confidential
Product Support Engineer
Responsibilities:
- Provide level 3 technical resolution services on escalated global support cases for telecom providers
- Assist customers in collecting captured data for discovery and Root Cause Analysis
- Conduct the sanity tests and software function and stress tests for the global customers