HEC Montréal

About: HEC Montréal is a education organization based out in Montreal, Quebec, Canada. It is known for research contribution in the topics: Context (language use) & Vehicle routing problem. The organization has 1221 authors who have published 5708 publications receiving 196862 citations. The organization is also known as: Ecole des Hautes Etudes Commerciales de Montreal & HEC Montreal.

Introduction to Location Science

Abstract: This chapter introduces modern Location Science. It traces the roots of the area and describes the path leading to the full establishment of this research field. It identifies several disciplines having strong links with Location Science and offers examples of areas in which the knowledge accumulated in the field of location has been applied with great success. It describes the purpose and structure of this volume. Finally, it provides suggestions on how to make use of the contents presented in this book, namely for organizing general or specialized location courses targeting different audiences.

Scaling models for the severity and frequency of external operational loss data

Abstract: According to Basel II criteria, the use of external data is indispensable to the implementation of an advanced method for calculating operational risk capital. This article investigates how the severity and frequencies of external losses are scaled for integration with internal data. We set up an initial model designed to explain the loss severity by taking into account potential selection bias in the external data. Estimation results show that many variables have significant power in explaining the loss amount. We use them to develop a normalization formula. We develop a zero-inflated count-data model to scale the loss frequency. We compute an operational VaR and we conduct out-of-sample backtesting.

Robustness of random forests for regression

Abstract: In this paper, we empirically investigate the robustness of random forests for regression problems. We also investigate the performance of six variations of the original random forest method, all aimed at improving robustness. These variations are based on three main ideas: (1) robustify the aggregation method, (2) robustify the splitting criterion and (3) taking a robust transformation of the response. More precisely, with the first idea, we use the median (or weighted median), instead of the mean, to combine the predictions from the individual trees. With the second idea, we use least-absolute deviations from the median, instead of least-squares, as splitting criterion. With the third idea, we build the trees using the ranks of the response instead of the original values. The competing methods are compared via a simulation study with artificial data using two different types of contaminations and also with 13 real data sets. Our results show that all three ideas improve the robustness of the original ra...