An important component of a suitably automated machine learning process is the automation of the model selection which often contains some optimal selection of hyperparameters. The hyperparameter optimization process is often conducted with a black-box tool, but, because different tools may perform better in different circumstances, automating the machine learning workflow might involve choosin...

In this chapter we survey several approaches to derive a recommendation from some preference models for multiple criteria decision aid. Depending on the specificities of the decision problem, the recommendation can be a selection of the best alternatives, a ranking of these alternatives or a sorting. We detail a sorting procedure for the assignment of alternatives to graded classes when the ava...

The Even Swap method, originally outlined by Benjamin Franklin 230 years ago, is a rational way of finding the best alternative by evenly swapping decision criteria. This study develops a Decision Ball model to assist a decision maker in ranking alternatives and visualizing decision process based on the Even Swap concept. By viewing the moving trajectories of alternatives on spheres, a decision...

Millions of malware samples are reported everyday, but cannot be carefully reviewed one by one due to the time limitation of human analysts. A ranking list to recommend the most important samples for our human analysts is thus desirable. In this thesis, we propose two different criteria to evaluate the importance of each sample. For each criterion, several popular algorithms are applied to choo...

Decision support systems can recommend strategies for disaster management, which can be further discussed by decision-makers. To provide rationales for the recommendations, the strategies need to be assessed according to relevant criteria. If several strategies are available, the criteria can be used for ranking the strategies. This paper addresses the issue concerning the choice of suitable cr...

This paper considers the problem of learning the ranking of' a set of' stochastic alternatives based upon incomplete information (i.e., a limited number of samples). We describe a system that, at each decision cycle, outputs either a complete ordering on the hypotheses or decides to gather additional information (Le., observations) at some cost. The ranking problem is a generalization of the pr...

Many data mining applications require a ranking, rather than a mere classification, of cases. Examples of these applications are widespread, including Internet search engines (ranking of pages returned) and customer relationship management(ranking of profitable customers). However, little theoretical foundation and practical guideline have been established to assess the merits of different rank...