The School of Mathematical and Computational Sciences welcomes the campus community to public research and teaching presentations by Dr. Rafiqul Chowdhury, candidate for the tenure track position in Data Science. All are welcome to attend.

Research Talk Title:  "Regressive class models using statistical and machine learning models for trajectory risk prediction of repeated categorical outcomes" 10am-11am

Abstract:  We proposed a regressive class modeling framework using machine learning algorithms to predict the trajectory of repeated multinomial outcomes. The proposed framework divides the data for each time point, applies the statistical and machine learning algorithms to each subset, and uses the Markov chain to recombine the results for trajectory risk prediction. The proposed framework will be effective in analyzing big data collected longitudinally. 

Teaching Talk titled:  "Model Selection" 1:30pm-2:30pm

Abstract:  This discussion will be on multiple linear regression and will cover such topics as:

• What is the model selection, and how do we select the best model, 
• Aspects of model selection for the regression problems, 
• Bias-variance trade-off, 
• Validation curve, 
• Illustrations using data sets, 
• The take-home message, and
• Python/R codes

Thursday, April 29- Research Talk 10am-11am/Teaching Talk 1:30pm-2:30pm

Via Zoom
https://zoom.us/j/99378457765?pwd=TDdpMURseXNlZHVtYjF5dUpqRm1Odz09

Meeting ID: 993 7845 7765
Passcode: 465725