Multi-objective evolutionary feature selection for online sales forecasting

Jimnez, F.; Snchez, G.; Garca, Jorge; Sciavicco, Guido; Miralles, Luis

doi:10.1016/j.neucom.2016.12.045

Cited by 104 publications

(58 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It also reduces storage requirements and computation time because the size of the data is also smaller. Thus, learning becomes an easier process (Jiménez, Sánchez, García, Sciavicco, & Miralles, ). The feature selection plays an important role which can directly influence the effectiveness of the resulting classification.…”

Section: The Proposed Moc‐aco‐minermentioning

confidence: 99%

Churn prediction in Turkey's telecommunications sector: A proposed multiobjective–cost‐sensitive ant colony optimization

Özmen

Aydoğan

Delice

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Players in the telecommunications sector struggle against the competition to keep customers, and therefore they need effective churn management. Most classification algorithms either ignore misclassification cost or assume that the costs of all incorrect classification errors are equal. But as in real life, many classification problems have different misclassification costs and this difference cannot be ignored. For this reason, studies on cost‐sensitive classification approaches have gained importance in recent years. The characteristics of telecommunications datasets such as high dimensionality and imbalance are making it difficult to achieve the desired performance for churn prediction. By taking this into consideration, we propose a multiobjective–cost‐sensitive ant colony optimization (MOC‐ACO‐Miner) approach which integrates the cost‐based nondominated sorted genetic algorithm feature selection and multiobjective ACO based cost‐sensitive learning. MOC‐ACO‐Miner is applied to one of Turkey's top 100 information technology companies for customer churn‐prediction. Finally, experiments find out that the model performs quite well with the area under receiver operating characteristic curve values of 0.9998 for predicting churners and therefore it can be beneficial for the highly competitive telecommunications sector. This article is categorized under: Algorithmic Development > Association Rules Application Areas > Industry Specific Applications Technologies > Prediction Technologies > Data Preprocessing

show abstract

Section: The Proposed Moc‐aco‐minermentioning

confidence: 99%

Churn prediction in Turkey's telecommunications sector: A proposed multiobjective–cost‐sensitive ant colony optimization

Özmen

Aydoğan

Delice

et al. 2019

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…(a) ENORA is a multiobjective evolutionary algorithm that has been intensively studied during the last decade: It has been applied to constrained real-parameter optimization (Jiménez et al, 2002), fuzzy optimization (Jiménez et al, 2013), fuzzy classification (Jiménez et al, 2014), and feature selection for regression (Jiménez et al, 2017), and, in this paper, we apply it to feature selection for classification and fuzzy classification in batch;…”

Section: Objectives Of the Workmentioning

confidence: 99%

“…We have not reproduced all the implementation details in this document because they are already described in Jiménez et al (2017) for feature selection and in Jiménez et al (2014) for fuzzy classification.…”

Section: Justification Of the Components Of The Multiobjective Evolutmentioning

confidence: 99%

Multiobjective evolutionary feature selection and fuzzy classification of contact centre data

Brunello

Jiménez

Marzano³

et al. 2019

Expert Systems

View full text Add to dashboard Cite

In this work, a data set describing phone interactions arising in a multichannel and multiskill contact centre is considered with the aim of classifying inbound sessions into those that will be eventually managed by an agent and those that, instead, will be abandoned before. More precisely, the goal of the work is to extract interpretable pieces of information that allow us to predict whether a user will or will not abandon a call, which may turn out to be very useful for the purpose of contact centre managing. To this end, the performance of two well‐known, state‐of‐the‐art evolutionary algorithms for feature selection (evolutionary nondominated radial slots based algorithm and nondominated sorted genetic algorithm) is compared for the task of feature selection, under the criteria of accuracy and cardinality of the selection, as well as for the task of fuzzy rule extraction, under the criteria of interpretability, accuracy, and hypervolume test. The best obtained fuzzy classifier, chosen after a decision making process, is validated and interpreted by domain experts.

show abstract

“…The results of the research express the acceptable performance of the proposed model, and the average 4% error is gained in comparison with the historical data. Jiménez et al (2017) proposed an approach to predict the sales of different products. The name of the approach proposed in this study is ENORA; it is in fact a type of evolutionary algorithm that is based on non-dominated sorting.…”

Section: Dynamic Strategic Managementmentioning

confidence: 99%

Developing a fuzzy inference system to devise proper business strategies: a study on carpet industry

et al. 2018

View full text Add to dashboard Cite

The present article formulates the scenarios that the organization will be probably facing with, using the uncertain factors in business environment, and it also selects the most robust strategies of organization for dealing with the formulated scenarios using the fuzzy information expressed by the experts in fuzzy inference system. The present article aims to provide a method enabling the scenario programmers to employ robustness philosophy using the scenario planning potentials and fuzzy inference system at the decision-making stage of the general process of strategy formulation. The process helps the strategic managers of the organizations to determine their business future clearly and enables them to select their robust scenario in the current market that is uncertain. After the introduction of the robust strategic planning methodology and illustrating its different stages, the selected strategies of them will be compared at the end of the article by implementing the strategic planning method in a practical case. The results of the research have been examined as a case study for carpet industry.

show abstract

Multi-objective evolutionary feature selection for online sales forecasting

Cited by 104 publications

References 65 publications

Churn prediction in Turkey's telecommunications sector: A proposed multiobjective–cost‐sensitive ant colony optimization

Churn prediction in Turkey's telecommunications sector: A proposed multiobjective–cost‐sensitive ant colony optimization

Multiobjective evolutionary feature selection and fuzzy classification of contact centre data

Developing a fuzzy inference system to devise proper business strategies: a study on carpet industry

Contact Info

Product

Resources

About