|
Dates : October 15, 22 and November 5, 12 3.30 pm,Seminar Hall Optimization, Business Analytics and Artificial Intelligence - A Brief Introduction Radhika Kulkarni Vice President, Advanced Analytics R&D at SAS Institute Inc. (Retired). 12-11-19 Abstract LECTURE ANNOUNCEMENT Title : Optimization, Business Analytics and Artificial Intelligence - A Brief Introduction A Four-Lecture Module introducing basic mathematical programming concepts and covering business applications in Analytics and Artificial Intelligence Speaker : Dr. Radhika Kulkarni, Vice President, Advanced Analytics R&D at SAS Institute Inc. (Retired) Dates : October 15, 22 and November 5, 12 Time : 3.30 pm Venue : Seminar Hall.
Overview: . Introduce the Business Analytics framework as a combination of multiple modeling techniques normally classified into descriptive, predictive and prescriptive methodologies. . Introduce the basic concepts of linear and integer programming as an example of prescriptive analytics techniques (assuming that students are already familiar with descriptive and predictive analytics) . Describe the challenges of applying analytics in the Big Data world — with examples of combining techniques from multiple disciplines to solve complex problems. A customer marketing problem of Offer Optimization will be used to illustrate in detail the mathematical challenges as data volumes increase along with practical implementation issues in a real world application. Some other examples in Retail, Manufacturing and other industries will be used to illustrate at a high level how combining multiple techniques from different domains leads to innovative solutions Where do all these techniques and innovations lead to in today’s world where Artificial Intelligence (AI) and Machine Learning (ML) have become part of our common vernacular? The last lecture will discuss applications ranging from health care to financial applications to manufacturing industries. In the world of big data and ML / AI tools, there are numerous opportunities for application of optimization techniques. Large scale implementation of machine learning tools in artificial intelligence platforms require automation at several levels – increasing productivity along the entire analytics lifecycle as well as automated model selection to improve predictive models.This final lecture will provide several examples that describe some of these innovations in various industries as well as discuss trends and upcoming challenges for future research. NOTE: A few code examples using the SAS Optimization Modeling language (PROC OPTMODEL) will be used to illustrate the use of software programs to solve the mathematical optimization problems. It is desirable that the students have a basic knowledge of statistics, predictive modeling (regression and classification) and linear programming.
|
