Steve Shao
Student

Lingyun (Steve) Shao is currently a M.S. student of the department of statistical science at Duke University. He is very enthusiastic about machine learning and had considerable experience of researches using different statistical learning methods (Xgboost, SVM, kNN and Neural Networks) and algorithms (ADMM, penalized regression). He is also very interested in the application of Bayesian statistical methods like MCMC. Interdisciplinary topics related to network data are also appealling to him since he had been a RA on network studies for long and his undergrad minor thesis is basically about transformation models in networks.

Lingyun earned his degree of B.S. in Statistics at School of Statistics, Renmin University of China, where he gained a solid background in statistics, math, programming. He also earned a Bacholar's degree of Economics in Economic Statistics and is equipped with knowledge of macro and micro economics, basic accounting, national accounting, finance, financial mathematics. Lingyun had been the research assistant of Prof. Yifan Sun at Renmin University of China for one year, focusing on optimal strategies and realization paths of game theory in networks. For experience in the industries, Lingyun had an internship of Model Analyst at Finupgroup, a e-finance company in Beijing, China and gained skills of build, test, assess credit risk model.


Lingyun is passionate about coding and algorithms. He is skilled at R, Matlab, Python and C. You can find him on github or kaggle by the nickname 'stveshawn' (which is basically the close version of 'steve'+'shao') and find some interesting stuff maybe.

Current Research Interests

Bayesian Statistics, Machine Learning,  Statistics on Network Data

Current Appointments & Affiliations

Contact Information

Some information on this profile has been compiled automatically from Duke databases and external sources. (Our About page explains how this works.) If you see a problem with the information, please write to Scholars@Duke and let us know. We will reply promptly.