Abstract
The link prediction task has found numerous applications in real-world scenarios. However, in most of the cases like interactions, purchases, mobility, etc., links can re-occur again and again across time. As a result, the data being generated is excessively large to handle, associated with the complexity and sparsity of networks. Therefore, we propose a very fast, memory-less, and dynamic sampling-based method for predicting recurring links for a successive future point in time. This method works by biasing the links exponentially based on their time of occurrence, frequency, and stability. To evaluate the efficiency of our method, we carried out rigorous experiments with massive real-world graph streams. Our empirical results show that the proposed method outperforms the state-of-the-art method for recurring links prediction. Additionally, we also empirically analyzed the evolution of links with the perspective of multi-graph topology and their recurrence probability over time.

Abstract
The smart cities concept - use of connected services and intelligent systems to support decision making in cities governance - aims to build better sustainability and living conditions for urban spaces, which are more complex every day. This work expects to optimize the waste collection circuits for non-residential customers in a city in Portugal. It is developed through the implementation of a simple, low-cost methodology when compared to commercial-available sensor systems. The main goal is to build a classifier for each client, being able to forecast the presence or absence of containers and, in a second step, predict how many containers of glass, paper or plastic would be available to be collected. Data were acquired during the period of one year, from January to December 2017, from more than 100 customers, resulting in a 26.000+ records dataset. Due to its degree of interpretability, we use Decision trees, implemented with a sliding window, which ran through the months of the year, stacking it one-by-one and/or merging few groups aiming the best correct predictions score. This project results in more efficient waste-collection routes, increasing the operation profits and reducing both costs and fuel-consumption, therefore diminishing it environmental footprint.

Abstract
The high asymmetry of international termination rates, where calls are charged with higher values, are fertile ground for the appearance of frauds in Telecom Companies. In this paper, we present three different and complementary solutions for a real problem called Interconnect Bypass Fraud. This problem is one of the most common in the telecommunication domain and can be detected by the occurrence of abnormal behaviours from specific numbers. Our goal is to detect as soon as possible numbers with abnormal behaviours, e.g. bursts of calls, repetitions and mirror behaviours. Based on this assumption, we propose: (i) the adoption of a new fast forgetting technique that works together with the Lossy Counting algorithm; (ii) the proposal of a single pass hierarchical heavy hitter algorithm that also contains a forgetting technique; and (iii) the application of the HyperLogLog sketches for each phone number. We used the heavy hitters to detect abnormal behaviours, e.g. burst of calls, repetition and mirror. The hierarchical heavy hitters algorithm is used to detect the numbers that make calls for a huge set of destinations and destination numbers that receives a huge set of calls to provoke a denial of service. Additionally, to detect the cardinality of destination numbers of each origin number we use the HyperLogLog algorithm. The results shows that these three approaches combined complements the techniques used by the telecom company and make the fraud task more difficult.

Abstract
The application of feature engineering in classification problems has been commonly used as a means to increase the classification algorithms performance. There are already many methods for constructing features, based on the combination of attributes but, to the best of our knowledge, none of these methods takes into account a particular characteristic found in many problems: causality. In many observational data sets, causal relationships can be found between the variables, meaning that it is possible to extract those relations from the data and use them to create new features. The main goal of this paper is to propose a framework for the creation of new supposed causal probabilistic features, that encode the inferred causal relationships between the target and the other variables. In this case, an improvement in the performance was achieved when applied to the Random Forest algorithm.

Abstract

Abstract
Classic feature selection techniques remove irrelevant or redundant features to achieve a subset of relevant features in compact models that are easier to interpret and so improve knowledge extraction. Most such techniques operate on the whole dataset, but are unable to provide the user with useful information when only instance-level information is required; in other words, classic feature selection algorithms do not identify the most relevant information in a sample. We have developed a novel feature selection method, called saliency-based feature selection (SFS), based on deep-learning saliency techniques. Our algorithm works under any architecture that is trained by using gradient descent techniques (Neural Networks, SVMs, ...), and can be used for classification or regression problems. Experimental results show our algorithm is robust, as it allows to transfer the feature ranking result between different architectures, achieving remarkable results. The versatility of our algorithm has been also demonstrated, as it can work either in big data environments as well as with small datasets.