Showing 4 results for Markov Chain
M. Ebrahimi, R. Farnoosh,
Volume 20, Issue 4 (4-2010)
Abstract
This paper is intended to provide a numerical algorithm based on random sampling for solving the linear Volterra integral equations of the second kind. This method is a Monte Carlo (MC) method based on the simulation of a continuous Markov chain. To illustrate the usefulness of this technique we apply it to a test problem. Numerical results are performed in order to show the efficiency and accuracy of the present method.
Mohammadjafar Tarokh, Mahsa Esmaealigookeh,
Volume 24, Issue 4 (12-2013)
Abstract
Abstract
Customer Lifetime Value (CLV) is known as an important concept in marketing and management of organizations to increase the captured profitability. Total value that a customer produces during his/her lifetime is named customer lifetime value. The generated value can be calculated through different methods. Each method considers different parameters. Due to the industry, firm, business or product, the parameters of CLV may vary. Companies use CLV to segment customers, analyze churn probability, allocate resources or formulate strategies related to each segment. In this article we review most presented models of calculating CLV. The aim of this survey is to gather CLV formulations of past 3 decades, which include Net Present Value (NPV), Markov chain model, probability model, RFM, survival analysis and so on.
Maryam Shekary Ashkezary, Amir Albadavi, Mina Shekari Ashkezari,
Volume 30, Issue 4 (12-2019)
Abstract
One of the key issues in the studies on customer relationship management (CRM) and modalities of marketing budget allocation is to calculate the customer’s lifetime value and applying it to macro-management decisions. A major challenge in this sector pertains to making calculations so as to incorporate the possibility of changes in the behavior of customers with the turn of time in the model.
In this article, we first classify the customers of ISACO using clustering techniques and use multilayer neural network to calculate the monetary value of each group of customers during the specific period of time. Then, we use the Markov chain approach to develop a model for calculating the lifetime value of ISACO’s customers by taking into consideration the possibility of changes in their behavior in future time periods.
In this study, a new approach has been used to estimate the parameters of the model proposed for calculating the future lifetime value of ISACO’s customers. This method takes into consideration the possibility of changes in the customer behavior throughout their interaction with the company.
The results obtained here may be used in the allocation of marketing budget and adoption of macro-management decisions to envisage various projects for customers with different lifetime value.
Pardis Roozkhosh, Amir Mohammad Fakoor Saghih,
Volume 35, Issue 3 (9-2024)
Abstract
The reliability of each component in a system plays a crucial role, as any malfunction can significantly reduce the system's overall lifespan. Optimizing the arrangement and sequence of heterogeneous components with varying lifespans is essential for enhancing system stability. This paper addresses the redundancy allocation problem (RAP) by determining the optimal number of components in each subsystem, considering their sequence, and optimizing multiple criteria such as reliability, cost uncertainty, and weight. A novel approach is introduced, incorporating a switching mechanism that accommodates both correct and defective switches. To assess reliability benefits, Markov chains are employed, while cost uncertainty is evaluated using the Monte-Carlo method with risk criteria such as percentile and mean-variance. The problem is solved using a modified genetic algorithm, and the proposed method is benchmarked against alternative approaches in similar scenarios. The results demonstrate a significant improvement in the Model Performance Index (MPI), with the best RAPMC solution under a mixed strategy achieving an MPI of 0.98625, indicating superior model efficiency compared to previous studies. Sensitivity analysis reveals that lower percentiles in the cost evaluations correlate with reduced objective function values and mean-variance, confirming the model's robustness in managing redundancy allocation to optimize reliability and control cost uncertainties effectively.