From Ensemble Learning to Meta-Analytics: A Review on Trends in Business Applications

Haque, Mohammad Nazmul; Moscato, Pablo

doi:10.1007/978-3-030-06222-4_18

“…The proposed approach involves the use of Radial Basis Function (RBF), Kriging, and Support Vector Regression (SVR) models in obtaining a predictor priority for a new order and thereby assigning the order schedule in the production. Haque and Moscato [16] provides a systematic review of trends in ensemble modelling in business applications. The result identified the following areas of business analytics for the successful application of ensemble modelling, including purchase and marketing analytics, predictive analytics, business process management analytics and customer churn analytics.…”

Section: A Ensembles In Supply Chain Management (Scm)mentioning

confidence: 99%

“…Brandtner et al [18] identified SCM processes such as customer activities, procurement, forecast and planning, packaging and handling, transportation, warehousing and inventory management with their data problems that can be addressed with ML analytics. The ensemble approaches in Inedi et al [13] and Haque et al [16] focused on forecast and planning SCM activities, while Safara [12] focused on customer activities. None of the papers provides a systematic ensemble approach that covers the majority of SCM activities.…”

Section: A Ensembles In Supply Chain Management (Scm)mentioning

confidence: 99%

“…None of the papers provides a systematic ensemble approach that covers the majority of SCM activities. Although Haque and Moscato [16] identified potential business areas for applying ensemble, it does not provide specific ensemble models and ensemble model constituents applicable to the identified business analytic use cases.…”

Section: A Ensembles In Supply Chain Management (Scm)mentioning

confidence: 99%

“…Previous research has shown the application of ensemble approaches in SC-related analytics and recently, due to Covid-19-related disruptions, the application of DA in SCM has received growing attention [11,12]. The research studies [12][13][14][15][16][17] show the application of ensemble approaches in different use cases in SCM. However, there is still a lack of research into a systematic approach to applying the ensemble model and corresponding model constituents for addressing data analytics problems and use cases in SCM analytics.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development of an Ensemble Modeling Framework for Data Analytics in Supply Chain Management

Udokwu,

Zimmermann,

Brandtner

et al. 2023

JAIT

1

0

View full text Add to dashboard Cite

The application of Data Analytics (DA) in Supply Chain Management (SCM) provides a plethora of opportunities for improving the performance, efficiency, and resilience of organizations by predicting the behaviour of the supply chain network. In this regard, the use of complex DA approaches that involve the combination of multiple Machine Learning (ML) models such as the ensemble approaches have shown to be highly effective in improving prediction accuracy and model performance. Still, the application of these ensemble approaches has not yet been properly explored in SCM analytics. Thus, this paper presents an ensemble model framework specifically designed for SCM issues by exploring problem types and use cases where ensemble approaches can be applied in SCM. The developed framework enables the selection of the right ensemble models for specific SCM DA tasks. Thus, this paper contributes to the scientific body of knowledge by presenting a systematic approach to ensemble modelling in SCM analytics by outlining suitable ensemble model compositions for different SCM use cases and data analytics problems. Hence the results of this paper provide a potential tool for DA practitioners in SCM to further improve the performance of their Supply Chain (SC) networks by selecting appropriate ensemble elements for different SCM analytics problems.

show abstract

“…The application of ensemble learning methods 21 has become ubiquitous across various domains, from healthcare 22 , nance 23,24 , image recognition 25 , natural language processing 26-28 , enabling informed decision-making and predictive analytics 29,30 . However, the e cacy of ensemble learning models heavily relies on the careful selection of hyperparameters 31 , con guration setting that dictate the learning process and in uence the model's generalization ability.…”

Section: Introductionmentioning

confidence: 99%

An Ensemble Learning Model for Forecasting Water-pipe Leakage

Warad,

Wassif,

Darwish

2024

Preprint

0

View full text Add to dashboard Cite

Based on the benefits of different ensemble methods, such as bagging and boosting, which have been studied and adopted extensively in research and practice, where bagging and boosting focus more on reducing variance and bias, this paper presented an optimization ensemble learning-based model for a large pipe failure dataset of water pipe leakage forecasting, something that was not previously considered by others. It is known that tuning the hyperparameters of each base learned inside the ensemble weight optimization process can produce better-performing ensembles, so it effectively improves the accuracy of water pipe leakage forecasting based on the pipeline failure rate. To evaluate the proposed model, the results are compared with the results of the bagging ensemble and boosting ensemble models using the root-mean-square error (RMSE), the mean square error (MSE), the mean absolute error (MAE), and the coefficient of determination (R2) of the bagging ensemble technique, the boosting ensemble technique and optimizable ensemble technique are higher than other models. The experimental result shows that the optimizable ensemble model has better prediction accuracy. The optimizable ensemble model has achieved the best prediction of water pipe failure rate at the 14th iteration, with the least RMSE = 0.00231 and MAE = 0.00071513 when building the model that predicts water pipe leakage forecasting via pipeline failure rate.

show abstract

An ensemble learning model for forecasting water-pipe leakage

Warad,

Wassif,

Darwish

2024

Sci Rep

2

0

View full text Add to dashboard Cite

Based on the benefits of different ensemble methods, such as bagging and boosting, which have been studied and adopted extensively in research and practice, where bagging and boosting focus more on reducing variance and bias, this paper presented an optimization ensemble learning-based model for a large pipe failure dataset of water pipe leakage forecasting, something that was not previously considered by others. It is known that tuning the hyperparameters of each base learned inside the ensemble weight optimization process can produce better-performing ensembles, so it effectively improves the accuracy of water pipe leakage forecasting based on the pipeline failure rate. To evaluate the proposed model, the results are compared with the results of the bagging ensemble and boosting ensemble models using the root-mean-square error (RMSE), the mean square error (MSE), the mean absolute error (MAE), and the coefficient of determination (R2) of the bagging ensemble technique, the boosting ensemble technique and optimizable ensemble technique are higher than other models. The experimental result shows that the optimizable ensemble model has better prediction accuracy. The optimizable ensemble model has achieved the best prediction of water pipe failure rate at the 14th iteration, with the least RMSE = 0.00231 and MAE = 0.00071513 when building the model that predicts water pipe leakage forecasting via pipeline failure rate.

show abstract

From Ensemble Learning to Meta-Analytics: A Review on Trends in Business Applications

Cited by 5 publications

References 87 publications

Development of an Ensemble Modeling Framework for Data Analytics in Supply Chain Management

Development of an Ensemble Modeling Framework for Data Analytics in Supply Chain Management

An Ensemble Learning Model for Forecasting Water-pipe Leakage

An ensemble learning model for forecasting water-pipe leakage

Contact Info

Product

Resources

About