Entity

Time filter

Source Type

Spain

Ruiz F.,Barcelonatech | Sama A.,Barcelonatech | Agell N.,ESADE URL
Frontiers in Artificial Intelligence and Applications | Year: 2012

Action learning is a methodology based on a machine learning system that makes it possible to select a suitable action or sequence of actions given a state. The main drawback of this methodology is the difficulty of assigning a class to the state-action pair to be included in the training set. This paper proposes an active learning methodology in the learning phase of an action learning process. With the help of an artificial example, the active methodology is compared with a passive methodology consisting of randomly selecting the training set from the pool of unlabelled patterns. © 2012 The authors and IOS Press. All rights reserved. Source


Casabayo M.,ESADE URL | Agell N.,ESADE URL | Sanchez-Hernandez G.,ESADE URL
Expert Systems with Applications | Year: 2014

This paper provides an innovative segmentation approach stemming from the combination of cluster analyses and fuzzy learning techniques. Our research provides a real case solution in the Spanish energy market to respond to the increasing number of requests from industry managers to be able to interpret ambiguous market information as realistically as possible. The learning stage is based on the segments created from a non-hierarchical cluster analysis. This results in fuzzy segmentation which permits patterns to be assigned to more than one segment. This in turn reveals that "fuzzifying" an excluding attitudinal segmentation offers more interpretable and acceptable results for managers. Our results demonstrate that 30% of the individuals show plural patterns of behaviour because they have a significant degree of adequacy to more than one segment. In such a rational market, this fact enables sales forces to develop more precise approaches to capture new customers and/or retain existing ones. © 2014 Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations