Multiple strategies based Grey Wolf Optimizer for feature selection in performance evaluation of open-ended funds

Swarm and Evolutionary Computation, Journal Year: 2024, Volume and Issue: 86, P. 101518 - 101518

Published: Feb. 24, 2024

Language: Английский

---

A Review on Machine Learning Methods for Customer Churn Prediction and Recommendations for Business Practitioners

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 70434 - 70463

Published: Jan. 1, 2024

Language: Английский

---

Renewable Energy Share in European Industry: Analysis and Extrapolation of Trends in EU Countries

Energies, Journal Year: 2024, Volume and Issue: 17(11), P. 2476 - 2476

Published: May 22, 2024

The strategic objective of world climate policy is the decarbonization industries, aiming to achieve “net-zero” emissions by 2050, as outlined in European Green Deal and Paris Agreement. This transition entails increasing utilization renewable energy sources (RES) industrial consumption, thereby transforming economies from reliance on fossil fuels sustainable alternatives. However, this shift poses a significant challenge for many EU countries, with varying degrees success adaptation. paper investigates process decarbonizing industries analyzing trends adoption RES countries evaluating their progress toward targets. Utilizing time series analysis production, total usage, proportion renewables study compares two groups countries: longstanding members newer additions. aim forecast trajectory integration industry assess feasibility meeting targets Deal. findings reveal considerable gap between set projected outcomes, only few expected meet EU’s 2030 goals. highlighted disparities shares across member states, ranging 0.0% 53.8% 2022. Despite notable increases absolute use energy, particularly central eastern nations, substantial challenges persist aligning sectors objectives.

Language: Английский

---

Improving Short-Term Photovoltaic Power Generation Forecasting with a Bidirectional Temporal Convolutional Network Enhanced by Temporal Bottlenecks and Attention Mechanisms

Electronics, Journal Year: 2025, Volume and Issue: 14(2), P. 214 - 214

Published: Jan. 7, 2025

Accurate photovoltaic (PV) power forecasting is crucial for effective smart grid management, given the intermittent nature of PV generation. To address these challenges, this paper proposes Temporal Bottleneck-enhanced Bidirectional Convolutional Network with Multi-Head Attention and Autoregressive (TB-BTCGA) model. It introduces a temporal bottleneck structure Deep Residual Shrinkage (DRSN) into (TCN), improving feature extraction reducing redundancy. Additionally, model transforms traditional TCN bidirectional (BiTCN), allowing it to capture both past future dependencies while expanding receptive field fewer layers. The integration an autoregressive (AR) optimizes linear features, inclusion multi-head attention Gated Recurrent Unit (BiGRU) further strengthens model’s ability short-term long-term in data. Experiments on complex datasets, including weather forecast data, station meteorological demonstrate that proposed TB-BTCGA outperforms several state-of-the-art deep learning models prediction accuracy. Specifically, single-step using data from three stations Hebei, China, reduces Mean Absolute Error (MAE) by 38.53% Root Square (RMSE) 33.12% increases coefficient determination (R2) 7.01% compared baseline multi-step forecasting, achieves reduction 54.26% best MAE 52.64% RMSE across various time horizons. These results underscore effectiveness its strong potential real-time grids.

Language: Английский

---

Efficient shrinkage temporal convolutional network model for photovoltaic power prediction

Energy, Journal Year: 2024, Volume and Issue: 297, P. 131295 - 131295

Published: April 15, 2024

Language: Английский

---

Bridging Predictive Insights and Retention Strategies: The Role of Account Balance in Banking Churn Prediction

AI, Journal Year: 2025, Volume and Issue: 6(4), P. 73 - 73

Published: April 10, 2025

The banking industry faces significant challenges, from high customer churn rates to threatening long-term revenue generation. Traditionally, models assess service quality using satisfaction metrics; however, these subjective variables often yield low predictive accuracy. This study examines the relationship between attrition and account balance decision trees (DT), random forests (RF), gradient-boosting machines (GBM). research utilises a dataset applies synthetic oversampling class distribution during preprocessing of financial variables. Account is primary factor in predicting churn, as it yields more accurate predictions compared traditional assessment methods. tested model set achieved its highest performance by applying boosting evaluation data highlights critical role indicators shaping effective retention strategies. By leveraging machine learning intelligence, banks can make informed decisions, attract new clients, mitigate risk, ultimately enhancing results.

Language: Английский

---

Estimating Calibrated Risks Using Focal Loss and Gradient-Boosted Trees for Clinical Risk Prediction

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1838 - 1838

Published: April 30, 2025

Probability calibration and decision threshold selection are fundamental aspects of risk prediction classification, respectively. A strictly proper loss function is used in clinical applications to encourage a model predict calibrated class-posterior probabilities or risks. Recent studies have shown that training with focal can improve the discriminatory power gradient-boosted trees (GBDT) for classification tasks an imbalanced skewed class distribution. However, not function. Therefore, output GBDT trained using accurate estimate true probability. This study aims address issue poor context applications. The methodology utilizes closed-form transformation confidence scores relates minimizer true-class posterior Algorithms based on Bayesian hyperparameter optimization provided choose parameter optimizes calibration, as measured by Brier score metric. We assess how affects optimize balanced accuracy, defined arithmetic mean sensitivity specificity. effectiveness proposed strategy was evaluated lung transplant data extracted from Scientific Registry Transplant Recipients (SRTR) predicting post-transplant cancer. also Behavioral Risk Factor Surveillance System (BRFSS) diabetes status. plots, slope intercept, show approach improves while maintaining same according area under receiver operating characteristics curve (AUROC) H-measure. focal-aware XGBoost achieved AUROC, score, 0.700, 0.128, 0.968 10-year cancer risk, miscalibrated equal AUROC but worse (0.140 1.579). method compared favorably standard cross-entropy (AUROC 0.755 versus 0.736 1-year cancer). Comparable performance observed other models task.

Language: Английский

---

Exploring land subsidence changes and its driving factors in mine areas: a case study in the Dagushan open-pit mine

Geosciences Journal, Journal Year: 2025, Volume and Issue: unknown

Published: April 28, 2025

Language: Английский

---

Mitigating class imbalance in churn prediction with ensemble methods and SMOTE

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: May 9, 2025

This study examines how imbalanced datasets affect the accuracy of machine learning models, especially in predictive analytics applications such as churn prediction. When are skewed towards majority class, it can lead to biased model performance, reducing overall effectiveness. To analyze this impact, research utilizes a dataset evaluate data imbalance influences accuracy. The utilized nine individual classifiers along with six homogeneous ensemble models effects on performance. Single classifier struggle identify underlying patterns data, while ensembles improve performance by focusing minority class. However, when trained unbalanced their remains subpar. top were selected for further investigation based data. A SMOTE sampling technique was employed create balanced dataset, ensuring that all classes adequately represented. generated model's improved from 61 79%, indicating removal bias target results showed Adaboost, an optimal classifier, demonstrated superior F1-Score 87.6% identifying potential and assessing customer account health. findings emphasize importance accurate ML predictions.

Language: Английский

---

Exploring Resampling Techniques in Credit Card Default Prediction

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: March 15, 2024

Abstract In the field of machine learning, preparation data is a pivotal step in optimizing model performance. This paper delves into crucial role cleaning and transformation, with particular emphasis on resampling techniques tailored for addressing imbalanced datasets. By emphasizing significance methodologies, this study underscores performance, especially when dealing Through an exploration both undersampling oversampling methods, their nuanced impacts classification performance explores potential trade-offs inherent each approach. Focusing domain credit card default prediction, research leverages UCI Credit Card dataset to provide comprehensive analysis. The results demonstrate that NearMiss outperformed other across all classifiers evaluation metrics. Similarly, K-MeansSMOTE emerged as top-performing technique Among investigated study, yielded highest accuracy. findings from enhance our understanding different contribute scholarship handling show pros cons methods used learning algorithms. They also how important customized are getting accurate predictions. While offering valuable insights, acknowledges necessity further refine generalize these diverse domains real-world applications, thereby contributing broader landscape methodologies.

Language: Английский

---