Calendar

Thursday, October 26
Mathematics Colloquium
03:35 PM - 04:30 PM
Location: Science Center Room 323
Cost: Free

Speaker: Tom Filloon, Stat.i.m llc

Host: Paul Eloe

Title: Visualizing & Validating CO$T Optimization (with JMP as your Analytic Hub)

Abstract: Using JMP’s Profiler capabilities, we were able to determine optimal ingredient proportions that simultaneously meet several key nutrient levels at a minimum cost. Using ingredients as ‘Columns’, Total Cost and Nutrient levels (e.g., Lysine) as new ‘Formula’ columns, and specifying Constraints (via scripting);  one can visualize, search & optimize the feasible  proportions of the individual ingredients that make up the final product formulation via JMP Profiler.  Furthermore, Custom Profiler was extremely useful for doing restricted optimization of subsets of ingredients by having the ability to set (ie. lock) specific ingredients levels to 0.  As this is essentially a linear programming problem, we wanted validate solutions against other software.  To this end, one can run either SAS (Proc Optmodel) and/or R (linprog package) code from within JMP via its analytic hub functionality.  This approach is fast, flexible, easily validated, and allows useful visualization for obtaining an optimal solution with any type of linear programming optimization problem.

Refreshments are available at 3:00 PM in SC 313F.

The department colloquia are held every Thursday (excluding holidays) at 3:35 pm in room SC 323 unless otherwise noted. All are invited to attend. 

Contact Information:
Name: Paul Eloe
Email: peloe1@udayton.edu