Mergani A. Khairalla

Ensemble selection is a crucial problem for ensemble learning (EL) to speed up the predictive model, reduce the storage space requirements and to further improve prediction accuracy. Diversity among individual predictors is widely recognized as a key factor to successful ensemble selection (ES), while the ultimate goal of ES is to improve its predictive accuracy and generalization of the ensemble. Motivated by the problems stated in previous, we have devised a novel hybrid layered based greedy ensemble reduction (HLGER) architecture to delete the predictor with lowest accuracy and diversity with evaluation function according to the diversity metrics. Experimental investigations are conducted based on benchmark time series data sets, support vectors regression algorithm utilized as base learner to generate homogeneous ensemble, HLGER uses locally weight ensemble (LWE) strategies to provide a final ensemble prediction. The experimental results demonstrate that, in comparison with benchmark ensemble pruning techniques, HLGER achieves significantly superior generalization performance.

Predicting students' dropout/stop-out and switch registration aspects at college is one of the important managerial issues that concern the academic institutions. This issue presents a specific challenge due to a large number of factors that can affect the student's decision and the imbalanced nature of the educational data. In this paper, a novel feature extraction method is applied to student satisfaction and socio-economic features during the pre-processing stage to reduce the high dimensionality of the data. Thus, different interpretable data mining approaches, including decision trees and rule induction methods, were examined using actual data of students at the Technical University of Palestine. After resolving imbalanced problem of the students' data, the results showed that the student satisfaction and socio-economic status predictors are important to distinguish different registration aspects. Moreover, the results revealed that J4.8 algorithm achieved best results due to the ability to apply an appropriate trade-off regarding accuracy versus interpretability.

In the real-life, time-series data comprise a complicated pattern, hence it may be challenging to increase prediction accuracy rates by using machine learning and conventional statistical methods as single learners. This research outlines and investigates the Stacking Multi-Learning Ensemble (SMLE) model for time series prediction problem over various horizons with a focus on the forecasts accuracy, directions hit-rate, and the average growth rate of total oil demand. This investigation presents a flexible ensemble framework in light of blend heterogeneous models for demonstrating and forecasting nonlinear time series. The proposed SMLE model combines support vector regression (SVR), backpropagation neural network (BPNN), and linear regression (LR) learners, the ensemble architecture consists of four phases: generation, pruning, integration, and ensemble prediction task. We have conducted an empirical study to evaluate and compare the performance of SMLE using Global Oil Consumption (GOC). Thus, the assessment of the proposed model was conducted at single and multistep horizon prediction using unique benchmark techniques. The final results reveal that the proposed SMLE model outperforms all the other benchmark methods listed in this study at various levels such as error rate, similarity, and directional accuracy by 0.74%, 0.020%, and 91.24%, respectively. Therefore, this study demonstrates that the ensemble model is an extremely encouraging methodology for complex time series forecasting.

Financial time‐series data have non‐linear and uncertain behavior which changes across the time. Therefore, the need to solve non‐linear, time‐variant problems has been growing rapidly. Traditional models such as statistical and data mining approach unable to cope with these issues. The main objective of this study to combine forecasts from the autoregressive integrated moving average model, exponential (EXP) model, and the multi‐layers perceptron (MLP) in a novel hybrid model. The analysis was based on financial data of Sudanese pound/EURO exchange rate in Sudan. In this case, simple additive combination and weight combination methods are used in combining linear and non‐linear models to produce hybrid forecast. Comparison between benchmark models and hybrid indicates that the hybrid model offers more accurate forecasts with reduced mean‐absolute percentage error of around 0.82% for all models over all forecasting horizons. Moreover, the results recommend that the non‐linear method can be applicable to an alternate to linear combining methods to accomplish better forecasting accuracy. On the basis of the results of this study, the authors can conclude that further experiments to estimate the weight of the combination methods and more models essential to be surveyed so as to explore innovative concerns in series prediction.