Results found: 2

Search results

Search:
in the keywords: C35

Sort By:

Limit search:

Hybrid C&RT-Logit Models In Churn Analysis

100%

Łapczyński M.

Folia Oeconomica Stetinensia

2014

vol. 14

issue 2

37-52

This article attempts to explain and predict the termination of relationships in telecommunications services by using the hybrid C&RT-logit model. The combination of decision trees (C&RT algorithm) with the logistic model enriches the model interpretation and sometimes improves the accuracy of prediction. Decision trees permit to detect interactions among variables and make the model resistant to outliers and to lack of data. On the other hand, the logistic model can extend the interpretation by using odds ratios. The solution delivered by the hybrid approach was compared with the decision tree model and the logistic model. Due to the difficulty in obtaining the real dataset from the Polish market, it was decided to build a model based on the data obtained from the repository http://www.dataminingconsultant.com/DMMM.htm . The models’ performance was estimated by using popular measures such as accuracy, recall, precision, true negative rate, G-mean, F measure and lift charts.

Computational Qualitative Economics – Using Computational Intelligence for Andvanced Learning of Economics in Knowledge Society

45%

Andrasik L.

Creative and Knowledge Society

2015

vol. 5

issue 2

1-15

In economics there are several complex learning themes and tasks connected with them difficult for deeper understanding of the learning subject. These are the reasons originating serious learning problems for students in the form of Virtual Environment because deeper understanding requires high level mathematical skills. Actually the most important feature for discerning this part of economics is the set of qualitative shapes emerging in discrete dynamic systems when they are undergoing iterations and/or experimentation with parameters and initial coordinates of variables. Among such shapes there are: - trajectories in evolving time; - trajectories in R2 of two variables; - cobweb portraits; - one control parameter bifurcation with first and/or with second variables; - two control parameters bifurcation in R2 (attractive basin of double controls); - cycles; - basin of attraction of two variables; - one Lyapunov’s exponent against some of control parameters; - Lyapunov’s exponents with two control parameters in R2; - absorbing area with possibility to create critical curves and/or attractors. The hope is that products of computational intelligence may help them solve such problems. Naturally, the meant complex economic problems and tasks have discrete, qualitative and nonlinear (noninvertible) nature resulting in increased level of difficulties. So with the term used in the head of this paper one has to understand narrowly: “qualitative nonlinear computational economics”. For better understanding the very nature of the problem we are using as appropriate example actual simulation of the model of new ICT products monopolies in virtual laboratory built in the routines setting dominantly in the software iDMC.

Refine search results

1 Creative and Knowledge Society

1 Folia Oeconomica Stetinensia

1 Andrasik L.

1 Łapczyński M.

1 2015

1 2014

Search results

Hybrid C&RT-Logit Models In Churn Analysis

Computational Qualitative Economics – Using Computational Intelligence for Andvanced Learning of Economics in Knowledge Society