Abstract
The rising fuel costs is disallowing random cruising strategies for passenger finding. Hereby, a recommendation model to suggest the most passengerprofitable urban area/stand is presented. This framework is able to combine the 1) underlying historical patterns on passenger demand and the 2) current network status to decide which is the best zone to head to in each moment. The major contribution of this work is on how to combine well-known methods for learning from data streams (such as the historical GPS traces) as an approach to solve this particular problem. The results were promising: 395.361/506.873 of the services dispatched were correctly predicted. The experiments also highlighted that a fleet equipped with such framework surpassed a fleet that is not: they experienced an average waiting time to pick-up a passenger 5% lower than its competitor. © 2013 IJCAI.

Abstract
Ensemble learning algorithms often benefit from pruning strategies that allow to reduce the number of individuals models and improve performance. In this paper, we propose a Metalearning method for pruning bagging ensembles. Our proposal differs from other pruning strategies in the sense that allows to prune the ensemble before actually generating the individual models. The method consists in generating a set characteristics from the bootstrap samples and relate them with the impact of the predictive models in multiple tested combinations. We executed experiments with bagged ensembles of 20 and 100 decision trees for 53 UCI classification datasets. Results show that our method is competitive with a state-of-the-art pruning technique and bagging, while using only 25% of the models.

Abstract
How to improve the performance of a simulated soccer team using final game statistics? This is the question this research aims to answer using model-based collaborative techniques and a robotic team - FC Portugal - as a case study. After developing a framework capable of automatically calculating the final game statistics through the RoboCup log files, a feature selection algorithm was used to select the variables that most influence the final game result. In the next stage, given the statistics of the current game, we rank the strategies that obtained the maximum average of goal difference in similar past games. This is done by splitting offline past games into different k-clusters. Then, for each cluster, the expected best strategy was assigned. The online phase consists in the selection of the expected best strategy for the cluster in which the current game best fits. Regarding the final results, our approach proved that it is possible to improve the performance of a robotic team by more than 35%, even in a competitive environment such as the RoboCup 2D simulation league.

Abstract
In soccer, like in other collective sports, although players try to hide their strategy, it is always possible, with a careful analysis, to detect it and to construct a model that characterizes their behavior throughout the game phases. These findings are extremely relevant for a soccer coach, in order not only to evaluate the performance of his athletes, but also for the construction of the opponent team model for the next match. During a soccer match, due to the presence of a complex set of intercorrelated variables, the detection of a small set of factors that directly influence the final result becomes almost an impossible task for a human being. In consequence of that, a huge number of software packages for analysis capable of calculating a vast set of game statistics appeared over the years. However, all of them need a soccer expert in order to interpret the produced data and select which are the most relevant variables. Having as a base a set of statistics extracted from the RoboCup 2D Simulation League log files and using a multivariable analysis, the aim of this research project is to identify which are the variables that most influence the final game result and create prediction models capable of automatically detecting soccer team behaviors. For those purposes, more than two hundred games (from 2006-2009 competition years) were analyzed according to a set of variables defined by a soccer experts board, and using the MARS and RReliefF algorithms. The obtained results show that the MARS algorithm presents a lower error value, when compared to RReliefF (from a pairwire t-test for a significance level of 5%). The p-value for this test was 2.2e-16 which means these two techniques present a significant statistical difference for this data. In the future, this work will be used in an offline analysis module, with the goal of detecting which is the team strategy that will maximize the final game result against a specific opponent.

Abstract
This paper proposes a framework to decompose and develop metafeatures for Metalearning (MtL) problems. Several metafeatures (also known as data characteristics) are proposed in the literature for a wide range of problems. Since MtL applicability is very general but problem dependent, researchers focus on generating specific and yet informative metafeatures for each problem. This process is carried without any sort of conceptual framework. We believe that such framework would open new horizons on the development of metafeatures and also aid the process of understanding the metafeatures already proposed in the state-of-the-art. We propose a framework with the aim of fill that gap and we show its applicability in a scenario of algorithm recommendation for regression problems.

Abstract
Nowadays, every public transportation company uses Automatic Vehicle Location (AVL) systems to track the services provided by each vehicle. Such information can be used to improve operational planning. This paper describes an AVL-based evaluation framework to test whether the actual Schedule Plan fits, in terms of days covered by each schedule, the network's operational conditions. Firstly, clustering is employed to group days with similar profiles in terms of travel times (this is done for each different route). Secondly, consensus clustering is used to obtain a unique set of clusters for all routes. Finally, a set of rules about the groups content is drawn based on appropriate decision variables. Each group will correspond to a different schedule and the rules identify the days covered by each schedule. This methodology is simultaneously an evaluator of the schedules that are offered by the company (regarding its coverage) and an advisor on possible changes to such offer. It was tested by using data collected for one year in a company running in Porto, Portugal. The results are sound. The main contribution of this paper is that it proposes a way to combine Machine Learning techniques to add a novel dimension to the Schedule Plan evaluation methods: the day coverage. Such approach meets no parallel in the current literature.