Search

We introduce the Robustness of Hierarchically Organized Time Series (RHiOTS) framework, designed to assess the robustness of hierarchical time series forecasting models and algorithms on real-world datasets. Hierarchical time series, where lower-level forecasts must sum to upper-level ones, are prevalent in various contexts, such as retail sales across countries. Current empirical evaluations of forecasting methods are often limited to a small set of benchmark datasets, offering a narrow view of algorithm behavior. RHiOTS addresses this gap by systematically altering existing datasets and modifying the characteristics of individual series and their interrelations. It uses a set of parameterizable transformations to simulate those changes in the data distribution. Additionally, RHiOTS incorporates an innovative visualization component, turning complex, multidimensional robustness evaluation results into intuitive, easily interpretable visuals. This approach allows an in-depth analysis of algorithm and model behavior under diverse conditions. We illustrate the use of RHiOTS by analyzing the predictive performance of several algorithms. Our findings show that traditional statistical methods are more robust than state-of-the-art deep learning algorithms, except when the transformation effect is highly disruptive. Furthermore, we found no significant differences in the robustness of the algorithms when applying specific reconciliation methods, such as MinT. RHiOTS provides researchers with a comprehensive tool for understanding the nuanced behavior of forecasting algorithms, offering a more reliable basis for selecting the most appropriate method for a given problem., Comment: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD '24), August 25--29, 2024, Barcelona, Spain

This paper studies the application of ensembles composed of multi-output models for multi-step ahead forecasting problems. Dynamic ensembles have been commonly used for forecasting. However, these are typically designed for one-step-ahead tasks. On the other hand, the literature regarding the application of dynamic ensembles for multi-step ahead forecasting is scarce. Moreover, it is not clear how the combination rule is applied across the forecasting horizon. We carried out extensive experiments to analyze the application of dynamic ensembles for multi-step forecasting. We resorted to a case study with 3568 time series and an ensemble of 30 multi-output models. We discovered that dynamic ensembles based on arbitrating and windowing present the best performance according to average rank. Moreover, as the horizon increases, most approaches struggle to outperform a static ensemble that assigns equal weights to all models. The experiments are publicly available in a repository., Comment: 19 pages, github repository available

This work aims to develop a computationally inexpensive approach, based on machine learning techniques, to accurately predict thousands of stellar rotation periods. The innovation in our approach is the use of the XGBoost algorithm to predict the rotation periods of Kepler targets by means of regression analysis. Therefore, we focused on building a robust supervised machine learning model to predict surface stellar rotation periods from structured data sets built from the Kepler catalogue of K and M stars. We analysed the set of independent variables extracted from Kepler light curves and investigated the relationships between them and the ground truth. Using the extreme gradient boosting method, we obtained a minimal set of variables that can be used to build machine learning models for predicting stellar rotation periods. Our models are validated by predicting the rotation periods of about 2900 stars. The results are compatible with those obtained by classical techniques and comparable to those obtained by other recent machine learning approaches, with the advantage of using much fewer predictors. Restricting the analysis to stars with rotation periods of less than 45 days, our models are on average 96 % correct. We have developed an innovative approach, based on a machine learning method, to accurately fit the rotation periods of stars. Based on the results of this study, we conclude that the best models generated by the proposed methodology are competitive with the state-of-the-art approaches, with the advantage of being computationally cheaper, easy to train, and relying on small sets of predictors., Comment: Paper submitted to A&A. Comments are welcome!

Significant wave height forecasting is a key problem in ocean data analytics. This task affects several maritime operations, such as managing the passage of vessels or estimating the energy production from waves. In this work, we focus on the prediction of extreme values of significant wave height that can cause coastal disasters. This task is framed as an exceedance probability forecasting problem. Accordingly, we aim to estimate the probability that the significant wave height will exceed a predefined critical threshold. This problem is usually solved using a probabilistic binary classification model or an ensemble of forecasts. Instead, we propose a novel approach based on point forecasting. Computing both type of forecasts (binary probabilities and point forecasts) can be useful for decision-makers. While a probabilistic binary forecast streamlines information for end-users concerning exceedance events, the point forecasts can provide additional insights into the upcoming future dynamics. The procedure of the proposed solution works by assuming that the point forecasts follow a distribution with the location parameter equal to that forecast. Then, we convert these point forecasts into exceedance probability estimates using the cumulative distribution function. We carried out experiments using data from a smart buoy placed on the coast of Halifax, Canada. The results suggest that the proposed methodology is better than state-of-the-art approaches for exceedance probability forecasting.

In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find instances of interest close to the decision boundary to drive the resampling process. However, under-sampling the majority class may potentially lead to important information loss. Over-sampling also may increase the chance of overfitting by propagating the information contained in instances from the minority class. The main contribution of our work is a new method called ICLL for tackling IBC tasks which is not based on resampling training observations. Instead, ICLL follows a layered learning paradigm to model the data in two stages. In the first layer, ICLL learns to distinguish cases close to the decision boundary from cases which are clearly from the majority class, where this dichotomy is defined using a hierarchical clustering analysis. In the subsequent layer, we use instances close to the decision boundary and instances from the minority class to solve the original predictive task. A second contribution of our work is the automatic definition of the layers which comprise the layered learning strategy using a hierarchical clustering model. This is a relevant discovery as this process is usually performed manually according to domain knowledge. We carried out extensive experiments using 100 benchmark data sets. The results show that the proposed method leads to a better performance relatively to several state-of-the-art methods for IBC.

Machine learning models are becoming increasingly popular in different types of settings. This is mainly caused by their ability to achieve a level of predictive performance that is hard to match by human experts in this new era of big data. With this usage growth comes an increase of the requirements for accountability and understanding of the models' predictions. However, the degree of sophistication of the most successful models (e.g. ensembles, deep learning) is becoming a large obstacle to this endeavour as these models are essentially black boxes. In this paper we describe two general approaches that can be used to provide interpretable descriptions of the expected performance of any black box classification model. These approaches are of high practical relevance as they provide means to uncover and describe in an interpretable way situations where the models are expected to have a performance that deviates significantly from their average behaviour. This may be of critical relevance for applications where costly decisions are driven by the predictions of the models, as it can be used to warn end users against the usage of the models in some specific cases.

The predictive advantage of combining several different predictive models is widely accepted. Particularly in time series forecasting problems, this combination is often dynamic to cope with potential non-stationary sources of variation present in the data. Despite their superior predictive performance, ensemble methods entail two main limitations: high computational costs and lack of transparency. These issues often preclude the deployment of such approaches, in favour of simpler yet more efficient and reliable ones. In this paper, we leverage the idea of model compression to address this problem in time series forecasting tasks. Model compression approaches have been mostly unexplored for forecasting. Their application in time series is challenging due to the evolving nature of the data. Further, while the literature focuses on neural networks, we apply model compression to distinct types of methods. In an extensive set of experiments, we show that compressing dynamic forecasting ensembles into an individual model leads to a comparable predictive performance and a drastic reduction in computational costs. Further, the compressed individual model with best average rank is a rule-based regression model. Thus, model compression also leads to benefits in terms of model interpretability. The experiments carried in this paper are fully reproducible.

Evaluating predictive models is a crucial task in predictive analytics. This process is especially challenging with time series data where the observations show temporal dependencies. Several studies have analysed how different performance estimation methods compare with each other for approximating the true loss incurred by a given forecasting model. However, these studies do not address how the estimators behave for model selection: the ability to select the best solution among a set of alternatives. We address this issue and compare a set of estimation methods for model selection in time series forecasting tasks. We attempt to answer two main questions: (i) how often is the best possible model selected by the estimators; and (ii) what is the performance loss when it does not. We empirically found that the accuracy of the estimators for selecting the best solution is low, and the overall forecasting performance loss associated with the model selection process ranges from 1.2% to 2.3%. We also discovered that some factors, such as the sample size, are important in the relative performance of the estimators.

Due to the surge of spatio-temporal data volume, the popularity of location-based services and applications, and the importance of extracted knowledge from spatio-temporal data to solve a wide range of real-world problems, a plethora of research and development work has been done in the area of spatial and spatio-temporal data analytics in the past decade. The main goal of existing works was to develop algorithms and technologies to capture, store, manage, analyze, and visualize spatial or spatio-temporal data. The researchers have contributed either by adding spatio-temporal support with existing systems, by developing a new system from scratch for processing spatio-temporal data, or by implementing algorithms for mining spatio-temporal data. The existing ecosystem of spatial and spatio-temporal data analytics can be categorized into three groups, (1) spatial databases (SQL and NoSQL), (2) big spatio-temporal data processing infrastructures, and (3) programming languages and software tools for processing spatio-temporal data. Since existing surveys mostly investigated big data infrastructures for processing spatial data, this survey has explored the whole ecosystem of spatial and spatio-temporal analytics along with an up-to-date review of big spatial data processing systems. This survey also portrays the importance and future of spatial and spatio-temporal data analytics.

Concept drift detection is a crucial task in data stream evolving environments. Most of state of the art approaches designed to tackle this problem monitor the loss of predictive models. However, this approach falls short in many real-world scenarios, where the true labels are not readily available to compute the loss. In this context, there is increasing attention to approaches that perform concept drift detection in an unsupervised manner, i.e., without access to the true labels. We propose a novel approach to unsupervised concept drift detection based on a student-teacher learning paradigm. Essentially, we create an auxiliary model (student) to mimic the behaviour of the primary model (teacher). At run-time, our approach is to use the teacher for predicting new instances and monitoring the mimicking loss of the student for concept drift detection. In a set of experiments using 19 data streams, we show that the proposed approach can detect concept drift and present a competitive behaviour relative to the state of the art approaches., Comment: 23 pages, single column

Fake news in social media has quickly become one of the most discussed topics in today's society. With false information proliferating and causing a significant impact in the political, economical, and social domains, research efforts to analyze and automatically identify this type of content have being conducted in the past few years. In this paper, we attempt to summarize the principal findings on the topic of fake news in social media, highlighting the main research path taken and giving a particular focus on the detection of fake news and bot accounts.

The early detection of anomalous events in time series data is essential in many domains of application. In this paper we deal with critical health events, which represent a significant cause of mortality in intensive care units of hospitals. The timely prediction of these events is crucial for mitigating their consequences and improving healthcare. One of the most common approaches to tackle early anomaly detection problems is standard classification methods. In this paper we propose a novel method that uses a layered learning architecture to address these tasks. One key contribution of our work is the idea of pre-conditional events, which denote arbitrary but computable relaxed versions of the event of interest. We leverage this idea to break the original problem into two hierarchical layers, which we hypothesize are easier to solve. The results suggest that the proposed approach leads to a better performance relative to state of the art approaches for critical health episode prediction.

Large amounts of mobility data are being generated from many different sources, and several data mining methods have been proposed for this data. One of the most critical steps for trajectory data mining is segmentation. This task can be seen as a pre-processing step in which a trajectory is divided into several meaningful consecutive sub-sequences. This process is necessary because trajectory patterns may not hold in the entire trajectory but on trajectory parts. In this work, we propose a supervised trajectory segmentation algorithm, called Wise Sliding Window Segmentation (WS-II). It processes the trajectory coordinates to find behavioral changes in space and time, generating an error signal that is further used to train a binary classifier for segmenting trajectory data. This algorithm is flexible and can be used in different domains. We evaluate our method over three real datasets from different domains (meteorology, fishing, and individuals movements), and compare it with four other trajectory segmentation algorithms: OWS, GRASP-UTS, CB-SMoT, and SPD. We observed that the proposed algorithm achieves the highest performance for all datasets with statistically significant differences in terms of the harmonic mean of purity and coverage.

Time series forecasting is one of the most active research topics. Machine learning methods have been increasingly adopted to solve these predictive tasks. However, in a recent work, these were shown to systematically present a lower predictive performance relative to simple statistical methods. In this work, we counter these results. We show that these are only valid under an extremely low sample size. Using a learning curve method, our results suggest that machine learning methods improve their relative predictive performance as the sample size grows. The code to reproduce the experiments is available at https://github.com/vcerqueira/MLforForecasting., Comment: 9 pages

Performance estimation aims at estimating the loss that a predictive model will incur on unseen data. These procedures are part of the pipeline in every machine learning project and are used for assessing the overall generalisation ability of predictive models. In this paper we address the application of these methods to time series forecasting tasks. For independent and identically distributed data the most common approach is cross-validation. However, the dependency among observations in time series raises some caveats about the most appropriate way to estimate performance in this type of data and currently there is no settled way to do so. We compare different variants of cross-validation and of out-of-sample approaches using two case studies: One with 62 real-world time series and another with three synthetic time series. Results show noticeable differences in the performance estimation methods in the two scenarios. In particular, empirical experiments suggest that cross-validation approaches can be applied to stationary time series. However, in real-world scenarios, when different sources of non-stationary variation are at play, the most accurate estimates are produced by out-of-sample methods that preserve the temporal order of observations.

Social media are becoming an increasingly important source of information about the public mood regarding issues such as elections, Brexit, stock market, etc. In this paper we focus on sentiment classification of Twitter data. Construction of sentiment classifiers is a standard text mining task, but here we address the question of how to properly evaluate them as there is no settled way to do so. Sentiment classes are ordered and unbalanced, and Twitter produces a stream of time-ordered data. The problem we address concerns the procedures used to obtain reliable estimates of performance measures, and whether the temporal ordering of the training and test data matters. We collected a large set of 1.5 million tweets in 13 European languages. We created 138 sentiment models and out-of-sample datasets, which are used as a gold standard for evaluations. The corresponding 138 in-sample datasets are used to empirically compare six different estimation procedures: three variants of cross-validation, and three variants of sequential validation (where test set always follows the training set). We find no significant difference between the best cross-validation and sequential validation. However, we observe that all cross-validation variants tend to overestimate the performance, while the sequential methods tend to underestimate it. Standard cross-validation with random selection of examples is significantly worse than the blocked cross-validation, and should not be used to evaluate classifiers in time-ordered data scenarios.

The profusion of user generated content caused by the rise of social media platforms has enabled a surge in research relating to fields such as information retrieval, recommender systems, data mining and machine learning. However, the lack of comprehensive baseline data sets to allow a thorough evaluative comparison has become an important issue. In this paper we present a large data set of news items from well-known aggregators such as Google News and Yahoo! News, and their respective social feedback on multiple platforms: Facebook, Google+ and LinkedIn. The data collected relates to a period of 8 months, between November 2015 and July 2016, accounting for about 100,000 news items on four different topics: economy, microsoft, obama and palestine. This data set is tailored for evaluative comparisons in predictive analytics tasks, although allowing for tasks in other research areas such as topic detection and tracking, sentiment analysis in short text, first story detection or news recommendation., Comment: Dataset available in http://www.dcc.fc.up.pt/~nmoniz/MultiSourceNews

Ranking evaluation metrics are a fundamental element of design and improvement efforts in information retrieval. We observe that most popular metrics disregard information portrayed in the scores used to derive rankings, when available. This may pose a numerical scaling problem, causing an under- or over-estimation of the evaluation depending on the degree of divergence between the scores of ranked items. The purpose of this work is to propose a principled way of quantifying multi-graded relevance judgments of items and enable a more accurate penalization of ordering errors in rankings. We propose a data-driven generation of relevance functions based on the degree of the divergence amongst a set of items' scores and its application in the evaluation metric Normalized Discounted Cumulative Gain (nDCG). We use synthetic data to demonstrate the interest of our proposal and a combination of data on news items from Google News and their respective popularity in Twitter to show its performance in comparison to the standard nDCG. Results show that our proposal is capable of providing a more fine-grained evaluation of rankings when compared to the standard nDCG, and that the latter frequently under- or over-estimates its evaluation scores in light of the divergence of items' scores., Comment: 12 pages, 4 figures

This document describes the R package UBL that allows the use of several methods for handling utility-based learning problems. Classification and regression problems that assume non-uniform costs and/or benefits pose serious challenges to predictive analytic tasks. In the context of meteorology, finance, medicine, ecology, among many other, specific domain information concerning the preference bias of the users must be taken into account to enhance the models predictive performance. To deal with this problem, a large number of techniques was proposed by the research community for both classification and regression tasks. The main goal of UBL package is to facilitate the utility-based predictive analytic task by providing a set of methods to deal with this type of problems in the R environment. It is a versatile tool that provides mechanisms to handle both regression and classification (binary and multiclass) tasks. Moreover, UBL package allows the user to specify his domain preferences, but it also provides some automatic methods that try to infer those preference bias from the domain, considering some common known settings.

The participatory Web has enabled the ubiquitous and pervasive access of information, accompanied by an increase of speed and reach in information sharing. Data dissemination services such as news aggregators are expected to provide up-to-date, real-time information to the end users. News aggregators are in essence recommendation systems that filter and rank news stories in order to select the few that will appear on the users front screen at any time. One of the main challenges in such systems is to address the recency and latency problems, that is, to identify as soon as possible how important a news story is. In this work we propose an integrated framework that aims at predicting the importance of news items upon their publication with a focus on recent and highly popular news, employing resampling strategies, and at translating the result into concrete news rankings. We perform an extensive experimental evaluation using real-life datasets of the proposed framework as both a stand-alone system and when applied to news recommendations from Google News. Additionally, we propose and evaluate a combinatorial solution to the augmentation of official media recommendations with social information. Results show that the proposed approach complements and enhances the news rankings generated by state-of-the-art systems., Comment: 17 pages, 2 figures, submitted to the ACM Transactions on Intelligent Systems and Technology (ACM TIST), Special Issue on Social Media Processing

Many real world data mining applications involve obtaining predictive models using data sets with strongly imbalanced distributions of the target variable. Frequently, the least common values of this target variable are associated with events that are highly relevant for end users (e.g. fraud detection, unusual returns on stock markets, anticipation of catastrophes, etc.). Moreover, the events may have different costs and benefits, which when associated with the rarity of some of them on the available training data creates serious problems to predictive modelling techniques. This paper presents a survey of existing techniques for handling these important applications of predictive analytics. Although most of the existing work addresses classification tasks (nominal target variables), we also describe methods designed to handle similar problems within regression tasks (numeric target variables). In this survey we discuss the main challenges raised by imbalanced distributions, describe the main approaches to these problems, propose a taxonomy of these methods and refer to some related problems within predictive modelling.

This document describes an infra-structure provided by the R package performanceEstimation that allows to estimate the predictive performance of different approaches (workflows) to predictive tasks. The infra-structure is generic in the sense that it can be used to estimate the values of any performance metrics, for any workflow on different predictive tasks, namely, classification, regression and time series tasks. The package also includes several standard workflows that allow users to easily set up their experiments limiting the amount of work and information they need to provide. The overall goal of the infra-structure provided by our package is to facilitate the task of estimating the predictive performance of different modeling approaches to predictive tasks in the R environment., Comment: Updated to version 1.0.2 of the R package. Added a small section on package installation. Made explicit the reference to the R package version number within the document

Many sciences have made significant breakthroughs by adopting online tools that help organize, structure and mine information that is too detailed to be printed in journals. In this paper, we introduce OpenML, a place for machine learning researchers to share and organize data in fine detail, so that they can work more effectively, be more visible, and collaborate with others to tackle harder problems. We discuss how OpenML relates to other examples of networked science and what benefits it brings for machine learning research, individual scientists, as well as students and practitioners., Comment: 12 pages, 10 figures