Person:
DUMAN, Ekrem

Profile Picture

Email Address

Birth Date

WoSScopusGoogle ScholarORCID

Name

Job Title

First Name

Ekrem

Last Name

DUMAN
OrgUnit Logo
Organizational Unit

Filters

2012 - 2019162020 - 20238
Reset filters

Settings

Publication Search Results

Now showing 1 - 10 of 25
  • Placeholder
    ArticlePublicationMetadata only
    VRP12 (vehicle routing problem with distances one and two) with side constraints
    (Elsevier, 2013-08) Ceranoglu, A. N.; Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem
    The problem undertaken in this study is inspired from a real life application. Consider a vehicle routing problem where the distances between the customer locations are either one or two. We name this problem as VRP12 in an analogy for the name TSP12 used for the traveling salesman problem in the literature. Additionally, assume that, the time to visit each customer is not constant and the visiting time together with the travel time constitutes the capacity of the vehicle. Furthermore, each customer has two characteristics and any two customers having a common characteristic should not be visited at the same time. If visited, a penalty fee incurs. In this study, we give the formulation of this problem and suggest some simple but effective algorithms that can be used to solve it. The algorithms are built with the relaxation of the side constraints but their performances are evaluated with their success in satisfying them. Information on our case study is also provided.
  • Placeholder
    Book PartPublicationMetadata only
    Intelligent classification-based methods in customer profitability modeling
    (Springer International Publishing, 2015) Ekinci, Y.; Duman, Ekrem; Industrial Engineering; Kahraman, C.; Onar, S. C.; DUMAN, Ekrem
    The expected profits from customers are important informations for the companies in giving acquisition/retention decisions and developing different strategies for different customer segments. Most of these decisions can be made through intelligent Customer Relationship Management (CRM) systems. We suggest embedding an intelligent Customer Profitability (CP) model in the CRM systems, in order to automatize the decisions that are based on CP values. Since one of the aims of CP analysis is to find out the most/least profitable customers, this paper proposes to evaluate the performances of the CP models based on the correct classification of customers into different profitability segments. Our study proposes predicting the segments of the customers directly with classification-based models and comparing the results with the traditional approach (value-based models) results. In this study, cost sensitive classification based models are used to predict the customer segments since misclassification of some segments are more important than others. For this aim, Classification and regression trees, Logistic regression and Chi-squared automatic interaction detector techniques are utilized. In order to compare the performance of the models, new performance measures are promoted, which are hit, capture and lift rates. It is seen that classification-based models outperform the previously used value-based models, which shows the proposed framework works out well.
  • Placeholder
    Conference ObjectPublicationMetadata only
    Applying migrating birds optimization to credit card fraud detection
    (Springer Science+Business Media, 2013) Elikucuk, I.; Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem
    We discuss how the Migrating Birds Optimization algorithm (MBO) is applied to statistical credit card fraud detection problem. MBO is a recently proposed metaheuristic algorithm which is inspired by the V flight formation of the migrating birds and it was shown to perform very well in solving a combinatorial optimization problem, namely the quadratic assignment problem. As analyzed in this study, it has a very good performance in the fraud detection problem also when compared to classical data mining and genetic algorithms. Its performance is further increased by the help of some modified neighborhood definitions and benefit mechanisms.
  • Placeholder
    ArticlePublicationMetadata only
    Migrating birds optimization: a new metaheuristic approach and its performance on quadratic assignment problem
    (Elsevier, 2012-12-25) Duman, Ekrem; Uysal, M.; Alkaya, A. F.; Industrial Engineering; DUMAN, Ekrem
    We propose a new nature inspired metaheuristic approach based on the V flight formation of the migrating birds which is proven to be an effective formation in energy saving. Its performance is tested on quadratic assignment problem instances arising from a real life problem and very good results are obtained. The quality of the solutions we report are better than simulated annealing, tabu search, genetic algorithm, scatter search, particle swarm optimization, differential evolution and guided evolutionary simulated annealing approaches. The proposed method is also tested on a number of benchmark problems obtained from the QAPLIB and in most cases it was able to obtain the best known solutions. These results indicate that our new metaheuristic approach could be an important player in metaheuristic based optimization.
  • Placeholder
    ArticlePublicationMetadata only
    Comparison of computational intelligence models on forecasting automated teller machine cash demands
    (Old City Publishing, 2020) Alkaya, A. F.; Gultekin, O. G.; Danaci, E.; Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem
    We take up the problem of forecasting the amount of money to be withdrawn from automated teller machines (ATM). We compare the performances of eleven different algorithms from four different research areas on two different datasets. The exploited algorithms are fuzzy time series, multiple linear regression, artificial neural network, autoregressive integrated moving average, gaussian process regression, support vector regression, long-short term memory, simultaneous perturbation stochastic approximation, migrating birds optimization, differential evolution, and particle swarm optimization. The first dataset is very volatile and is obtained from a Turkish bank whereas the more stationary second dataset is obtained from a UK bank which was used in competitions previously. We use mean absolute deviation (MAD) to compare the algorithms since it provides a universal comparison ability independent of the magnitude of the data. The results show that support vector regression (SVR) performs the best on both data sets with a very short run time.
  • Placeholder
    Conference ObjectPublicationMetadata only
    Profit-based artificial neural network (ANN) trained by migrating birds optimization: a case study in credit card fraud detection
    (World Academy of Science, Engineering and Technology, 2015) Zakaryazad, Ashkan; Duman, Ekrem; Kibekbaev, Azamat; Industrial Engineering; DUMAN, Ekrem; Zakaryazad, Ashkan; Kibekbaev, Azamat
    A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.
  • Placeholder
    Conference ObjectPublicationMetadata only
    Turkish cashier problem with time windows and its solution by Migrating bird optimization algorithm
    (IEEE, 2023) Bassaleh, Ahmad; Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem; Bassaleh, Ahmad
    A new application of the traveling salesman problem referred to as the Turkish cashier problem (TCP) was recently introduced in literature. The problem revolved around a cashier that must visit several locations and return to his office. To complete his visits, he can use taxis or public transportation and the objective is to minimize the total transportation cost. To make this problem more practical, we took time into consideration by adding a soft time interval for each location obligating the cashier to make his visit within. If he fails to visit within the adequate time, a penalty must be paid. We name this problem as the TCP with time windows (TCPwTW). A metaheuristic algorithm known as the Migrating Birds Optimization (MBO) algorithm coupled with mathematical programming was developed to solve TCPwTW. We attempted to find the exact optimum using an exact solver where for complex problems, optimal solutions cannot be found. The quantitative study reveals that for problems having a loose time interval, the Solver serves as the best approach. On the other hand, for problems having tight time intervals, the best solutions can be obtained by the matheuristic.
  • Placeholder
    ArticlePublicationMetadata only
    Social media analytical CRM: a case study in a bank
    (IOS Press, 2023) Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem
    The use of the social media (SM) has become more and more widespread during the last two decades, the companies started looking for insights for how they can improve their businesses using the information accumulating therein. In this regard, it is possible to distinguish between two lines of research: those based on anonymous data and those based on customer specific data. Although obtaining customer specific SM data is a challenging task, analysis of such individual data can result in very useful insights. In this study we take up this path for the customers of a bank, analyze their tweets and develop three kinds of analytical models: clustering, sentiment analysis and product propensity. For the latter one, we also develop a version where, besides the text information, the structural information available in the bank databases are also used in the models. The result of the study is a considerably more efficient set of analytical CRM models.
  • Placeholder
    ArticlePublicationMetadata only
    A novel collection optimisation solution maximising long-term profits: a case study in an international bank
    (Taylor & Francis, 2017-10-02) Duman, Ekrem; Ecevit, F.; Çakır, Ç.; Altan, O.; Industrial Engineering; DUMAN, Ekrem
    When customers fail to pay the amount they owe to their bank related with a credit product (credit cards, overdraft accounts or instalment loans), the bank starts the collection process. This process typically lasts for a particular amount of time after which the customer is labelled as defaulted and a litigation period is launched. Banks try to minimise the percentage of credit exposure that goes to litigation since it negatively affects the bank’s profitability. Accordingly, they take various actions to maximise the collections before litigation. In this study, we approach this problem from a different perspective as we maximise not the short-term collections but the long-term revenues from customers by incorporating the churn effects of these actions in our modelling. © 2018 Informa UK Limited, trading as Taylor & Francis Group.
  • Thumbnail Image
    ArticlePublicationOpen Access
    Deep reinforcement learning approach for trading automation in the stock market
    (IEEE, 2022) Kabbani, Taylan; Duman, Ekrem; Industrial Engineering; DUMAN, Ekrem; Kabbani, Taylan
    Deep Reinforcement Learning (DRL) algorithms can scale to previously intractable problems. The automation of profit generation in the stock market is possible using DRL, by combining the financial assets price 'prediction' step and the 'allocation' step of the portfolio in one unified process to produce fully autonomous systems capable of interacting with their environment to make optimal decisions through trial and error. This work represents a DRL model to generate profitable trades in the stock market, effectively overcoming the limitations of supervised learning approaches. We formulate the trading problem as a Partially Observed Markov Decision Process (POMDP) model, considering the constraints imposed by the stock market, such as liquidity and transaction costs. We then solve the formulated POMDP problem using the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm reporting a 2.68 Sharpe Ratio on unseen data set (test data). From the point of view of stock market forecasting and the intelligent decision-making mechanism, this paper demonstrates the superiority of DRL in financial markets over other types of machine learning and proves its credibility and advantages in strategic decision-making.