Search results

1 – 3 of 3
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 27 May 2021

Sara Tavassoli and Hamidreza Koosha

Customer churn prediction is one of the most well-known approaches to manage and improve customer retention. Machine learning techniques, especially classification algorithms, are…

552

Abstract

Purpose

Customer churn prediction is one of the most well-known approaches to manage and improve customer retention. Machine learning techniques, especially classification algorithms, are very popular tools to predict the churners. In this paper, three ensemble classifiers are proposed based on bagging and boosting for customer churn prediction.

Design/methodology/approach

In this paper, three ensemble classifiers are proposed based on bagging and boosting for customer churn prediction. The first classifier, which is called boosted bagging, uses boosting for each bagging sample. In this approach, before concluding the final results in a bagging algorithm, the authors try to improve the prediction by applying a boosting algorithm for each bootstrap sample. The second proposed ensemble classifier, which is called bagged bagging, combines bagging with itself. In the other words, the authors apply bagging for each sample of bagging algorithm. Finally, the third approach uses bagging of neural network with learning based on a genetic algorithm.

Findings

To examine the performance of all proposed ensemble classifiers, they are applied to two datasets. Numerical simulations illustrate that the proposed hybrid approaches outperform the simple bagging and boosting algorithms as well as base classifiers. Especially, bagged bagging provides high accuracy and precision results.

Originality/value

In this paper, three novel ensemble classifiers are proposed based on bagging and boosting for customer churn prediction. Not only the proposed approaches can be applied for customer churn prediction but also can be used for any other binary classification algorithms.

Details

Kybernetes, vol. 51 no. 3
Type: Research Article
ISSN: 0368-492X

Keywords

Access Restricted. View access options
Article
Publication date: 20 July 2015

Hamidreza Koosha and Amir Albadvi

The purpose of this paper is to allocate marketing budgets in complex environments, where data are scarce and management judgment is available. In this research, marketing budgets…

1440

Abstract

Purpose

The purpose of this paper is to allocate marketing budgets in complex environments, where data are scarce and management judgment is available. In this research, marketing budgets are allocated, to maximize customer equity as a long-term profitability measure.

Design/methodology/approach

The researchers provide a model for allocation of marketing budgets based on both decision calculus and econometric models and combine it with the concept of Markov chain model to cope with data scarcity. Dynamic programming is used to find the optimal solution.

Findings

The authors examine the model in telecommunication industry. Applicability of the model is supported by an illustrative example. To allocate marketing budgets, researchers consider three strategies for each period: do nothing, retention-focused strategy and acquisition-focused strategy. The results show the applicability and effectiveness of the model to find the best strategy.

Research limitations/implications

As the suggested approach is based on management judgment, it is useful in situations, as the authors have experts or experienced managers to achieve reliable data. In situations which the authors do not have access to experienced managers, the results may be unreliable.

Practical implications

The suggested approach is useful in situations of data scarcity, where experienced managers are accessible. The researchers have focused on telecommunication industry cases; however, the model is useful in other industries like the insurance industry.

Originality/value

The main contribution of the research lies in the suggestion of a new approach to allocate marketing budgets in data scarcity situations in multi-period planning horizons. The researchers use both decision calculus and econometric tools to find the transition matrices of marketing plans.

Details

Journal of Modelling in Management, vol. 10 no. 2
Type: Research Article
ISSN: 1746-5664

Keywords

Access Restricted. View access options
Article
Publication date: 3 May 2011

Amir Albadvi and Hamidreza Koosha

The main purpose of this research is to find an optimal allocation of marketing budgets which maximizes customer equity in an uncertain environment. Since markets are naturally…

2189

Abstract

Purpose

The main purpose of this research is to find an optimal allocation of marketing budgets which maximizes customer equity in an uncertain environment. Since markets are naturally uncertain environments, the aim is to incorporate uncertainty into the model.

Design/methodology/approach

Researchers have developed a mathematical programming model which employs customer equity as an objective function in order to allocate marketing budgets. The robust optimization approach is employed to tackle the proposed model, which deals with uncertainty.

Findings

The solution of the robust model is shown to be feasible and satisfactory in all uncertain situations. The robust solutions (of the presented model) are stable in volatile situations; while if the solution of deterministic models is used, it may be suboptimal or even infeasible. Sensitivity analysis of the deterministic solution only describes how stable is the suggested solution, but a robust optimization approach always provides a stable solution.

Research limitations/implications

The presented model will be most effective where uncertainty is high; if uncertainty is not a matter of concern or estimates are reliable, deterministic models are also effective.

Practical implications

Companies periodically decide on marketing budgets in order to achieve predefined marketing targets in future periods. The results of this research may be useful and applicable in marketing departments for allocating marketing budgets, especially in uncertain environments.

Originality/value

The main contribution of this research lies in providing an approach to allocate marketing budgets in uncertain environments. Unlike previous studies, the presented method takes into account the uncertainty of parameters in a systematic way. Hence, in case of high degrees of uncertainty, the use of robust optimization is strictly recommended.

Details

Management Decision, vol. 49 no. 4
Type: Research Article
ISSN: 0025-1747

Keywords

1 – 3 of 3
Per page
102050