Peihua Gu

WORK HISTORY

EDUCATION

SKILLS

ABOUT PEIHUA GU

8 years’ experience in statistical modeling and machine learning techniques, including regularization, decision trees, bagging, random forest, gradient boosting method, deep learning, linear regression, logistic regression, generalized linear models, double generalized linear model, mediation models, generalized estimating equations, linear mixed models, Kaplan-Meier method, Cox proportional hazards model, time series models, piecewise linear models, cross-validation, bootstrap and jackknife resampling method, variable clustering, predictive modeling and model validation• Excellent hands-on skills developing automation tools using Python or SAS for data-mining and statistical analysis in epidemiology, clinical research, marketing research and insurance predictive modeling research• Experience with Databricks, R, Python, Spark, SAS EM, SAS EG, Snowflake, Teradata, Oracle, Hadoop/Hive• Experience with R packages such as caret, xgboost, gbm, randomForest, e1071, tm, arules, arulesCBA, etc.• Knowledge with Text Mining • Experience with Python packages including NumPy, Matplotlib, Seaborn, SciKit-Learn, Papermill, Xgboost, Shap, Keras, etc• Familiar with PySpark, MLlibTools: Databricks, Snowflake, SAS EG, SAS EM, R, Anaconda, Apache Spark, Ultraedit, Hue, Oracle, Teradata, Tableau, etc.SAS/STAT procedures used: proc reg, proc glm, proc genmod, proc mixed, proc nlmixed, proc transreg, proc glmselect, proc hpgenselect, proc surveyselect, proc power, proc plan, proc phreg, proc lifetest, proc logistic, proc varclus, proc cluster, proc tree, proc arbor, proc princomp, proc prinqual, etc.My SAS blog: sasshowcase.wordpress.com