Skip to main content

Decision Aiding Through a Multiple Criteria Method Based on (Dis)similarity for Nominal Classification

Online Event |

As part of CEGIST's seminar cycle, we are proud to announce that Prof. Ana Sara Costa (CEGIST) will be presenting the work "Decision Aiding Through a Multiple Criteria Method Based on (Dis)similarity for Nominal Classification",

This seminar will take place on May 14 at 15h30, online, via Zoom (link below).

https://videoconf-colibri.zoom.us/j/85734973000?pwd=dW9ibGVqUXJzU1NZR2Y0N2dsbHFnZz09

Our seminars are free to attend and open to everyone. Please share with whomever may be interested.

Ana Sara Costa
Ana Sara Costa

 

 

 

 

 

 

 

 

 

 

 

 

 

 


Summary

The plethora of classification problems in various real-world decision situations motivated us to develop an innovative multiple criteria decision aiding (MCDA) method. This kind of problems usually involves a set of criteria for assessing the objects of the decision (also called actions) and assigning them to categories that are previously predefined. If they are preferentially ordered, we face an ordinal classification or sorting problem, otherwise, we face a nominal classification problem. We present CAT-SD (CATegorization by Similarity Dissimilarity), an MCDA method designed for nominal classification that innovates by considering (subjective) similarity and dissimilarity between two actions, and the potential interaction effects between criteria. The construction of the decision model using CAT-SD depends on the preferences and judgments of the Decision Maker (DM). We show the web based decision support system where CAT-SD has been implemented, called DECSPACE. It is focused on the user experience, and it aims to provide an easy-to-use interface and an intuitive approach for applying MCDA methods. We describe two studies applying CAT SD: the first one is related to the recruitment and selection process of Special Forces for the Portuguese Army, and the second one is focused on the adaptive reuse of underused buildings for cultural purposes in the city of Turin, Italy. Both studies were conducted using a constructive approach for building a decision model, based on a set of interaction protocols, which involves an interactive process between the DM and the analyst. Indeed, the applicability of the method is diverse. Our research outcomes can bring an added value to the DM, their organizations, and our society.

 

Speaker's bio

Ana Sara Costa is an Invited Assistant Professor at the Department of Engineering and Management of Instituto Superior Técnico of Universidade de Lisboa (IST-ULisboa) and a researcher at the Center for Management Studies of IST (CEGIST). She obtained her Ph.D. in Engineering and Management at IST-ULisboa in 2020. She has a Master’s degree in Biomedical Engineering from NOVA School of Science and Technology and a Post-Graduation in Project Management from ISEG Executive Education. Her current research interests are in the areas of Multiple Criteria Decision Aiding, Decision Support Systems and Management.