Search

School dropout is a relevant socio-economic problem across the globe. Predictive models have been developed to determine the likelihood of students dropping out of their studies precociously to overcome such a problem. Academic systems, which gather data from many students, are potential sources for datasets that feed dropout prediction algorithms, thus leading to general improvements in education quality. Despite successful past attempts to predict dropout, several works depict small datasets with features that are hard to reproduce. Furthermore, predicting whether a student will drop out is not enough to diagnose and prevent the problem as it is also necessary to provide potential justifications for the dropout. This paper proposes an approach for creating and enriching a dataset for dropout prediction, which has been applied for dropout prediction using data from 19 schools in Brazil. With this dataset and using classifiers and model explaining techniques, our experiments achieved Area Under the Precision–Recall Curve (AUC-PR) scores of up to 89.5%, Precision up to 95%, Recall up to 93%, and Kolmogorov–Smirnov (KS) rates up to 97% when predicting dropout at different year moments. This study also shows differences when predicting dropouts in different educational stages, such as preschool and secondary education, with the former being more complex than the latter. In addition to the high recognition rates, our proposal identifies potential reasons for student dropout, which are relevant for educational institutions to take preemptive actions. • Dropout prediction is performed with educational, financial, and public data. • Dropout analysis is conducted in different educational stages and time of the year. • Explainable machine learning allows reasoning behind potential dropouts. [ABSTRACT FROM AUTHOR]

• IoT and machine learning promote soil moisture forecast for smart irrigation. • Our approach is fully data-driven and independent of domain-knowledge features. • Results come from twelve fields on four farms, from eight crop types in four years. • Boosting outperforms neural networks, and blended models improve performance. • Poor data quality is a challenge for machine learning soil moisture forecast. The rise of the Internet of Things allowed higher spatial–temporal resolution soil moisture data captured through in situ sensing. Such abundance of data enables machine learning-based soil moisture forecast as an alternative to traditional mechanistic approaches for irrigation water need estimation. This paper develops a guideline for soil moisture forecast modeling based on machine learning, tested in a real case analysis comprehending eight crop types in twelve fields from four farms distributed over diverse climatic scenarios in Brazil. Instead of a single value, we predict the following days' minimum and maximum values as targets to monitor risks of extreme soil moisture values. Furthermore, modeling soil moisture directly in volumetric water content (VWC) is better than modeling soil matric potential (SMP) to later convert in soil moisture VWC. We test several algorithms and find out that LightGBM outperforms linear regression, decision tree, random forest, multilayer perceptron, LSTM, and StemGNN. Also, blending predictions via algorithm ensemble provides an additional accuracy gain. For model training and accuracy measurement, we use weighted datasets to privilege rare but critical data points. We show that soil moisture forecast reaches its maximum performance considering only past soil moisture, a context-aware index, and a precipitation forecast. Finally, we demonstrate that traditional domain-knowledge features - such as evapotranspiration, crop phenology, and soil hydraulic behavior - are not relevant to improving SM forecast performance. Consequently, our paper suggests full data-driven approaches for irrigation water need estimation, observed some care regarding data quality. [ABSTRACT FROM AUTHOR]

This paper focuses on a medium-term distribution plan for a pharmaceutical network, considering distribution center (DC) location and transportation decisions. The problem is characterized by low DC opening costs due to outsourced warehousing services. Therefore, transportation costs have a higher impact on location decisions and should be carefully evaluated. In addition, medicines vary widely in sales price and volume, demand behavior, and physical characteristics, which affects the distribution planning. This paper proposes a multi-product, multi-period, and multi-modal mathematical model integrating network design and distribution planning decisions, such as product flow, transportation modes, type of freight shipping, fleet sizing, and escorting services for high-value cargo. The mathematical formulation takes into consideration realistic features such as value-added tax, whose rate varies among locations. A Local Branching matheuristic taking advantage of the hierarchical problem structure is introduced. The result of tests using real-life data demonstrate the model's effectiveness to support the trade-off between the location and transportation problem, corroborating the relevance of making these decisions simultaneously. A comparison of the results with a company shows opportunities to reduce overall logistics costs plus the total amount of chargeable taxes. Regarding computational running times, the proposed matheuristic outperformed CPLEX in 75% of instances. • Focus on the medium-term distribution planning for multiple high-value products. • A location–transportation problem considering value-added tax issues is addressed. • We deal with issues such as freight types, cargo insurance, and escorting decisions. • The study was motivated by a real case of a global pharmaceutical company in Brazil. • The problem is solved using a Local Branching based heuristic. [ABSTRACT FROM AUTHOR]

Expensive multi-objective combinatorial optimization problems have constraints in the number of objective function evaluations due to time, financial, or resource restrictions. As most combinatorial problems, they are subject to a high number of duplicated solutions. Given the fact that expensive environments limit the number of objective function evaluations, the existence of duplicated solutions heavily impacts the optimization process due to poor diversity and low convergence speed. This paper proposes the Novel-First Tabu Search, a greedy-strategy mechanism that uses Knowledge-Assisted Local Search methods to preserve the population diversity and increase the exploration and exploitation ability of MOEA/D. Experiments are conducted on constrained, unconstrained, multimodal, deceptive, linear, convex, and non-convex Pareto Front multi-objective combinatorial optimization benchmark problems. This paper also conducts an experiment on the real-world, expensive problem of Well Placement Optimization using a benchmark case based on the Namorado oil field, located in the Campos Basin, Brazil. The experimental results and performance comparison with state-of-the-art algorithms demonstrate that the proposed design significantly preserves diversity and increases convergence without violating the constraint in the number of objective function evaluations. • A greedy strategy that uses knowledge-assisted local search methods is developed. • The greedy strategy is combined with the MOEA/D algorithm. • The method is evaluated on five well-known multi-objective combinatorial problems. • The method is evaluated on the real-world problem of Well Placement Optimization. • It achieves faster convergence in comparison with state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Highlights: [•] In this paper, efficiency in Brazilian banking is measured using a two-stage process. [•] Results indicate that Brazilian banks are heterogeneous. [•] Cost efficiency is explained by M&A and size. [•] Productive efficiency is explained M&A and public status. [•] Policy implications for the Brazilian banking sector are also derived. [Copyright &y& Elsevier]

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system — a cascade-based operation scenario. For this, we propose a new mathematical modeling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multi-objective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out. • An efficient Multi-objective Evolutionary Swarm Hybrid algorithm is proposed. • Development of a nonlinear model to operational control of Hydro-power plants. • Hydro-power plant data regression obtains the maximum efficiency of the power units. • Efficiency energy goals achieved an increasing the profit in the energy production. [ABSTRACT FROM AUTHOR]

• We analyze the correlation of meteorological and human mobility in Brazilian capitals. • We propose the EEMD-ARIMAX method to predict time series with independent variables. • We introduce an anomaly detection algorithm to adjust the prediction. In 2020, Brazil was the leading country in COVID-19 cases in Latin America, and capital cities were the most severely affected by the outbreak. Climates vary in Brazil due to the territorial extension of the country, its relief, geography, and other factors. Since the most common COVID-19 symptoms are related to the respiratory system, many researchers have studied the correlation between the number of COVID-19 cases with meteorological variables like temperature, humidity, rainfall, etc. Also, due to its high transmission rate, some researchers have analyzed the impact of human mobility on the dynamics of COVID-19 transmission. There is a dearth of literature that considers these two variables when predicting the spread of COVID-19 cases. In this paper, we analyzed the correlation between the number of COVID-19 cases and human mobility, and meteorological data in Brazilian capitals. We found that the correlation between such variables depends on the regions where the cities are located. We employed the variables with a significant correlation with COVID-19 cases to predict the number of COVID-19 infections in all Brazilian capitals and proposed a prediction method combining the Ensemble Empirical Mode Decomposition (EEMD) method with the Autoregressive Integrated Moving Average Exogenous inputs (ARIMAX) method, which we called EEMD-ARIMAX. After analyzing the results poor predictions were further investigated using a signal processing-based anomaly detection method. Computational tests showed that EEMD-ARIMAX achieved a forecast 26.73% better than ARIMAX. Moreover, an improvement of 30.69% in the average root mean squared error (RMSE) was noticed when applying the EEMD-ARIMAX method to the data normalized after the anomaly detection. [ABSTRACT FROM AUTHOR]

Abstract: Statistical methods have been widely employed to assess the capabilities of credit scoring classification models in order to reduce the risk of wrong decisions when granting credit facilities to clients. The predictive quality of a classification model can be evaluated based on measures such as sensitivity, specificity, predictive values, accuracy, correlation coefficients and information theoretical measures, such as relative entropy and mutual information. In this paper we analyze the performance of a naive logistic regression model () and a logistic regression with state-dependent sample selection model () applied to simulated data. Also, as a case study, the methodology is illustrated on a data set extracted from a Brazilian bank portfolio. Our simulation results so far revealed that there is no statistically significant difference in terms of predictive capacity between the naive logistic regression models and the logistic regression with state-dependent sample selection models. However, there is strong difference between the distributions of the estimated default probabilities from these two statistical modeling techniques, with the naive logistic regression models always underestimating such probabilities, particularly in the presence of balanced samples. [Copyright &y& Elsevier]

Abstract: In this paper a two-phase data envelopment analysis approach is proposed in order to examine in a separated way the operational and financial performances for airlines. Empirical results are based on panel data from Brazilian and American airlines, using data from 34 observations (within the period from 1997 to 2006), and shows that for the emergent market, operational performance is always much better than the financial one, showing that the resources optimization has been the main concern for these companies. Also, results for this market show that improving the operational efficiency does not necessarily generate an improvement in financial efficiency. Future research should ascertain whether or not these results replicate in companies other than airlines. [Copyright &y& Elsevier]

Abstract: The present paper studies the informational content of the Brazilian term structure of interest rate. We apply multiresolution decomposition to the spread and to the industrial production, and investigate if the term spread presents information that can help predict the path followed by industrial production. We also investigate if all the predictive ability of the spread is due to the monetary policy. The results suggest that the yield spread contains relevant information, and this predictive power varies across time patterns. Inasmuch, the results indicate that the predictive power of the spread is not totally explained by monetary policy. [Copyright &y& Elsevier]

Abstract: Since almost all anthropogenic activities ultimately affect the coastal waters, access properties and processes in this environment is the major issue in decision making and system management. Particularly, seasonal patterns are not clear in tropical areas, therefore, requiring environmental classification. The knowledge of long-term biogenic element dynamics, the biological response, and the selection of indicators connecting lower and higher trophic levels have became a real need for the sustainable management of marine resources. Under this scenario, this paper uses a machine-learning approach to determine the ecological status of coastal waters based on patterns of occurrence of meroplankton larvae of epibenthic fauna and its relationship with other environmental variables. The case studied is the upwelling influenced bay at Cabo Frio Island (Rio de Janeiro – Brazil) because this location has been suffering with anthropogenic impact. Models of crisp and fuzzy rules have been tested as classifiers. Results show it is possible to access hidden patterns of water masses within a set of association rules. [Copyright &y& Elsevier]

Abstract: In the present paper we apply multiresolution decomposition in order to test if the Brazilian yield spread has informational content in the prediction of inflation. Additionally, we investigate the effect of the implementation of inflation targeting regime over this relation. The results suggest that the predictive power of the spread varies across time patterns. Inasmuch, the results indicate that the implementation of the inflation target regime was a sine qua non condition for a substantial increase in the predictive power of inflation. Overall, results suggest that wavelets transformations may be very useful in the building of forecasts of important financial variables. [Copyright &y& Elsevier]