SUMMARY

• Skillful in applied analytics, risk analytics, predictive analytics, descriptive statistics, feature extraction, pattern Confidential, data mining, machine learning, data reporting and Confidential
• Expertise in machine learning: regression, support vector machine, decision trees, ensemble learning, clustering, causal Confidential, neural networks and deep learning
• AI/ML: Keras, TensorFlow, Scikit - learn, Anaconda Navigator ( Confidential, Spyder, Orange, RStudio)
• Excellent skills in analyzing data, drawing insights, interpreting data, creating reports or dashboards in a precise, cohesive, compelling and timely manner

TECHNICAL SKILLS

BI Reporting Tools: Tableau, Microstrategy, Qlikview, Crystal Reports, Cognos, MS PowerPoint, SSRS, Power BI, Power Point, Access and Excel

Big Data Tools: Apache Spark and Hadoop (Hive, Pig, HDFS, HBase, MapReduce)

Analytical tools: SQL, R, Python, SAS, SPSS, Toad, Orange and Google Analytics

Cloud Computing: AWS (EC2, S3, RDS DB), Azure (Data Factory and Lake), GCP Hands-on experience with MS SQL SERVER(2012, 2014, 2016), ACCESS, ORACLE (11g, 12c), SAP databases, and knowledgeable about PostgreSQL, MySQL, NoSQL, DB2, and Teradata

Strong in Microsoft BI Stack: SSAS, SSRS, SSIS, Power Pivot, Power Query, Power View, Power BI, Other ETL Tools Datastage, Informatica, Pentaho, TalendSolution provider, problem solver, and self-motivated learner with creative and critical thinking

PROFESSIONAL EXPERIENCE

Data Analytics Lead

Confidential, Pittsburgh, PA

Responsibilities:

• Routinely provide customary analysis and standard reports for internal or external stakeholders with ad hoc reports, daily automations, weekly or monthly updates, quarterly or yearly reviews
• Apply predictive analytics in Confidential, identify the risk factors and features for employee attrition and build a working model of employee churn with ensemble learning method: Confidential Regression, Confidential, Neural Network, CART and Random Forest
• Cooperate with client’s HRIS group, identify the bottlenecks for the workload of the reporting ticket system with advanced analytics approach, provide and deploy the business solution, and achieve the improvement of work efficiency with 2.5X increase
• Further develop, implement and maintain the client's reporting and analytics system with standardized procedures and coach other analytics staff in reporting and data Confidential
• Continue to provide the consultation on predictive analytics modeling, data mining, and statistical analysis, as required on accounts for Business Senior Leadership for the following projects: Employee Loyalty Analysis/Attrition Risk, Employee Sentiment and Fraud Risk Management, Predicting HR Capacity and Recruitment Needs, Talent Acquisition Pipeline Candidate Analysis, Sales and Marketing Forecasting, and Employee Profiling and Job Performance
• Teach client’s analytics staffs with hands-on demonstration on how to process, clean, audit and validate data from their raw datasets and apply in predictive analytics modeling, data mining, and statistical analysis
• Design, develop, test and deploy predictive models to drive business improvements, develop strategic plan and support business decision-making

Confidential, Pittsburgh, PA

Data Scientist

Responsibilities:

• Searched and collected data from different data sources with Python, extracted and filtered related information with SQL, statistically analyzed the data to draw the insights with SAS or R, visualized data to find trends with dashboards either by Tableau or PowerBI, and identified the pattern to build the predictive models for further solutions with R packages or Python libraries
• Analyzed data, drew conclusions, summarized findings in tables, graphs or figures, created research reports or presentation, produced documents such as manuscripts, publications or grant proposals for principal investigators in their applying for research funds from various funding sources including NIH, NSF and other foundations with total awards worth about $ 4.78 millions
• Provided service of large scale data mining of various databases by using advanced statistical and machine learning models with bioinformatics validation, and interpreted complex high-throughput NGS datasets with statistical methods and implemented bioinformatics algorithms for high-dimensional GWAS data analysis
• Implemented the Support Vector Machine Learning algorithm and efficiently predicted functional gene regulator from human genome and validated with ENCODE ChIP-seq database
• Trained biomedical researchers and students on bioinformatics tools, statistical methods and High-Performance Computing Resource (PSC, SaM)
• Involved in Causal Confidential and Statistical Reasoning of biomedical big data: Cancer Signaling Pathway project, Liver-specific Disease project, and Obesity associated Diabetes project
• Participated in The Cancer Genome Atlas(TCGA) and Cancer Personalized Medicine programs
• Involved in the Pittsburgh Genome Resource Repository (PGRR) and Confidential Enterprise Data Warehouse
• Participated in the Precision Medicine Initiative (PMI) Cohort Program: Precision Approach to healthCARE (PA CARES)

Confidential, Pittsburgh, PA

Data Analyst

Responsibilities:

• Analyzed and managed multi-omics datasets relevant to the study of genomes and molecular network evolution in several translational research projects
• Provided consultation in planning, modeling, designing, developing, implementing, administering, and maintaining various Databases
• Provided solutions with MS SQL Server Stack Packages: Reporting Services (SSRS), MS SQL Server Integration Services (SSIS) and MS SQL Server Analysis Services (SSAS)
• Provided the SAS statistical programing service, and created customized reports and processes in SAS and Tableau for HER/EMR and clinical trial data
• Involved in the outcomes research for liver transplantation, cost effectiveness research, health disparities, patient safety and quality by using the large Confidential observational datasets
• Improved existing data management systems, provided reporting support, and conducted research analyses
• Developed and implemented programs to process and manipulate preclinical and clinical datasets
• Wrote queries for extracting data, prepared reports with both tabular and graphical presentations, and developed statistical and computational models
• Helped in designing, testing, and implementing clinical data reporting systems for the clinical staff
• Built a small database of patient liver tissue and serum bank for Confidential liver center
• Identified IT technical and data issues that arose and worked with the project team
• Conducted statistical analyses and summarized the results, documented statistical programming procedures