Yazar "Boru, Asli" seçeneğine göre listele

Listeleniyor 1 - 9 / 9
  • [ X ]
    Öğe
    A Novel Hybrid Artificial Intelligence Based Methodology for the Inventory Routing Problem
    (Mdpi, 2019) Boru, Asli; Dosdogru, Ayse Tugba; Gocken, Mustafa; Erol, Rizvan
    In this paper, a new hybrid method including simulation optimization and artificial intelligence based simulation is created to solve the inventory routing problem (IRP) in which three different routing strategies are evaluated for uneven demand patterns including intermittent, erratic, and lumpy demand. The proposed method includes two phases. In the first phase, a nondominated sorting genetic algorithm II based simulation is employed to perform a multi-objective search for the IRP where the objectives of the method are total supply chain cost minimization and average service level maximization. In the second phase, artificial neural network based simulation is used to adjust the reorder point and order-up-to-level by forecasting the customer demand at each replenishment time. The results of the study demonstrated that the average service level is at least 98.54% in the supply chain. From this, it can be concluded that the proposed method can provide a tremendous opportunity to improve the average service level under uncertain environments. In addition, it is determined that different routing strategies can be selected for different demand patterns according to the considered performance measures.
  • [ X ]
    Öğe
    Characterizing continuous (s, S) policy with supplier selection using Simulation Optimization
    (Sage Publications Ltd, 2017) Gocken, Mustafa; Dosdogru, Ayse Tugba; Boru, Asli; Geyik, Faruk
    A real-world inventory control system, due to its nonlinear, stochastic, time-dependent nature, and the presence of complex interactions between supply chain members, can become quite challenging to optimize and requires a complex model. At this point, the Simulation Optimization (SO) model gains a better understanding of the complex and messy phenomenon of the inventory control of supply chain members. By creating SO models for Distribution Center (DC)s and Suppliers, we wish to present flexible and comprehensible research on the important decision of whether to minimize the differences between total overordering cost and total underordering cost (Model 1) or to minimize the total supply chain cost (Model 2). We also try to point out several important issues: the optimal value of the initial inventory, the reorder point, and the order-up-to level in continuous (s, S) policy for each DC and each Supplier; whether SO models can successfully integrate the supplier selection and continuous (s, S) policy for the supply chain environment; how to apply statistical analysis skills to compare these SO models with a greater level of detail. According to the cost analysis, the total supply chain cost of Model 1 is improved approximately 22% with Model 2. Also, Model 2 is the best one according to quantity-based analysis, order-based analysis, probability-based analysis, and lead-time-based analysis. Model 2 can be successfully applied for the actual situation of the supply chain inventory system and companies can obtain a remarkable amount of saving while increasing their competitive edge.
  • [ X ]
    Öğe
    Hybridizing Extreme Learning Machine and Bio-Inspired Computing Approaches for Improved Stock Market Forecasting
    (IEEE, 2017) Gocken, Mustafa; Boru, Asli; Dosdogru, Ayse Tugba; Ozcalici, Mehmet
    Under today's economic conditions, developing more robust and realistic forecasting methods is needed to make investments more profitable and secure. However, understanding the structure of the stock markets is very difficult because of the dynamic and non-stationary data. In this context, bio-inspired computing approaches including evolutionary computation and swarm intelligence can be used to make more accurate calculations and forecasting results. This paper improved Extreme Learning Machine (ELM) using Genetic Algorithm (GA), Differential Evolution (DE) as a two evolutionary computation methods, and Particle Swarm Optimization (PSO) and Weighted Superposition Attraction (WSA) as a two swarm intelligence methods for stock market forecasting in Turkey. The results of this study show that proposed methods can be successfully used in any real-time stock market forecasting because of the noteworthy improvement in forecasting accuracy.
  • [ X ]
    Öğe
    Hybridizing Extreme Learning Machine and bio-inspired computing approaches for improved stock market forecasting
    (Institute of Electrical and Electronics Engineers Inc., 2017) Göçken, Mustafa; Boru, Asli; Dosdo?ru, Ayşe Tu?ba; Özçalici, Mehmet
    Under today's economic conditions, developing more robust and realistic forecasting methods is needed to make investments more profitable and secure. However, understanding the structure of the stock markets is very difficult because of the dynamic and non-stationary data. In this context, bio-inspired computing approaches including evolutionary computation and swarm intelligence can be used to make more accurate calculations and forecasting results. This paper improved Extreme Learning Machine (ELM) using Genetic Algorithm (GA), Differential Evolution (DE) as a two evolutionary computation methods, and Particle Swarm Optimization (PSO) and Weighted Superposition Attraction (WSA) as a two swarm intelligence methods for stock market forecasting in Turkey. The results of this study show that proposed methods can be successfully used in any real-time stock market forecasting because of the noteworthy improvement in forecasting accuracy. © 2017 IEEE.
  • [ X ]
    Öğe
    Integrating metaheuristics and ANFIS for daily mean temperature forecasting
    (Inderscience Enterprises Ltd, 2016) Gocken, Mustafa; Boru, Asli
    Weather forecasting is considered as a key to successful planning for various applications such as agricultural industries. Having accurate weather forecasting allows people to make better decision on managing day to day activities. Also, it has to be underlined that forecasting is important to cope with impacts of extreme events and to adapt to climatic changes. To improve weather forecasting, we used hybrid adaptive neuro-fuzzy inference system (ANFIS), which consist in exploiting capabilities of harmony search (HS) and genetic algorithm (GA), for selecting the most relevant weather variables and simultaneously searching the most appropriate structure of ANFIS. Proposed methods are applied for six different cities of Turkey which are determined according to Aydeniz's climate classification. The results of the study showed that GA-ANFIS and HS-ANFIS yield remarkable results in daily mean temperature forecasting due to the ability of capturing the advantages of both types of methods simultaneously.
  • [ X ]
    Öğe
    Integrating metaheuristics and Artificial Neural Networks for improved stock price prediction
    (Pergamon-Elsevier Science Ltd, 2016) Gocken, Mustafa; Ozcalici, Mehmet; Boru, Asli; Dosdogru, Ayse Tugba
    Stock market price is one of the most important indicators of a country's economic growth. That's why determining the exact movements of stock market price is considerably regarded. However, complex and uncertain behaviors of stock market make exact determination impossible and hence strong forecasting models are deeply desirable for investors' financial decision making process. This study aims at evaluating the effectiveness of using technical indicators, such as simple moving average of close price, momentum close price, etc. in Turkish stock market. To capture the relationship between the technical indicators and the stock market for the period under investigation, hybrid Artificial Neural Network (ANN) models, which consist in exploiting capabilities of Harmony Search (HS) and Genetic Algorithm (GA), are used for selecting the most relevant technical indicators. In addition, this study simultaneously searches the most appropriate number of hidden neurons in hidden layer and in this respect; proposed models mitigate well-known problem of overfitting/underfitting of ANN. The comparison for each proposed model is done in four viewpoints: loss functions, return from investment analysis, buy and hold analysis, and graphical analysis. According to the statistical and financial performance of these models, HS based ANN model is found as a dominant model for stock market forecasting. (C) 2015 Elsevier Ltd. All rights reserved.
  • [ X ]
    Öğe
    (R, s, S) inventory control policy and supplier selection in a two-echelon supply chain: An Optimization via Simulation approach
    (Institute of Electrical and Electronics Engineers Inc., 2016) Gocken, Mustafa; Boru, Asli; Dosdogru, Ayse Tugba; Geyik, Faruk
    Existing literature proves that Optimization via Simulation (OvS) is relatively easy to develop regardless of the complexity of the problem and provide a much more realistic solution methodology without assumption. Hence, we used OvS to determine optimal (R, s, S) policy for Distribution Center (DC)s and suppliers and to properly select the suppliers for DCs under stochastic environmental condition and lost sales system. Determining the optimal parameters, especially determining reorder point and order-up-to level, are major challenges for (R, s, S) policy and hence, their optimal values are determined by means of OvS. Also, initial inventories of DCs and suppliers are considered because the initial conditions of a simulation are crucial aspects of simulation modeling. The proposed OvS model can be helpful for managers to understand better the scope of both the problem at hand and opportunities associated with inventory management. © 2015 IEEE.
  • [ X ]
    Öğe
    (R, s, S) INVENTORY CONTROL POLICY AND SUPPLIER SELECTION IN A TWO-ECHELON SUPPLY CHAIN: AN OPTIMIZATION VIA SIMULATION APPROACH
    (IEEE, 2015) Gocken, Mustafa; Boru, Asli; Dosdogru, Ayse Tugba; Geyik, Faruk
    Existing literature proves that Optimization via Simulation (OvS) is relatively easy to develop regardless of the complexity of the problem and provide a much more realistic solution methodology without assumption. Hence, we used OvS to determine optimal (R, s, S) policy for Distribution Center (DC) s and suppliers and to properly select the suppliers for DCs under stochastic environmental condition and lost sales system. Determining the optimal parameters, especially determining reorder point and order-up-to level, are major challenges for (R, s, S) policy and hence, their optimal values are determined by means of OvS. Also, initial inventories of DCs and suppliers are considered because the initial conditions of a simulation are crucial aspects of simulation modeling. The proposed OvS model can be helpful for managers to understand better the scope of both the problem at hand and opportunities associated with inventory management.
  • [ X ]
    Öğe
    Stock price prediction using hybrid soft computing models incorporating parameter tuning and input variable selection
    (Springer London Ltd, 2019) Gocken, Mustafa; Ozcalici, Mehmet; Boru, Asli; Dosdogru, Ayse Tugba
    Over the years, high-dimensional, noisy, and time-varying natures of the stock markets are analyzed to carry out accurate prediction. Particularly, speculators and investors are understandably eager to accurately predict stock price since millions of dollars flow through the stock markets. At this point, soft computing models have empowered them to capture the data patterns and characteristics of stock markets. However, one of the open problems in soft computing models is how to systematically determine architecture of models for given applications. In this study, Harmony Search is utilized to optimize the architecture of Neural Network, Jordan Recurrent Neural Network, Extreme Learning Machine, Recurrent Extreme Learning Machine, Generalized Linear Model, Regression Tree, and Gaussian Process Regression for 1-, 2-, 3-, 5-, 7-, and 10-day-ahead stock price prediction. The experimental results show worthy findings of stock market behavior over different prediction terms and stocks. This study also helps researchers understand which prediction model performed the best and how different conditions affect the prediction accuracy of the models. Proposed hybrid models can be successfully used by speculators and investors to make the investment or to hedge against potential risk in stock markets.