Abstract
The difficulty of making decisions and the development of mathematics,
mathematical applications to achieve the best solution in complex systems has led to the
emergence. Which is one of the applications of mathematical optimization, management,
economics, planning, engineering includes many areas such as methods of providing the
best solution. Today's businesses to use resources efficiently, fund surpluses must
strengthen systems to assess the decision-making in order to achieve such objectives.With
globalization in a rapidly changing business and economic way to adapt to its environment, decision-makers to broaden the decision-making systems passes. A
mathematical model, describing a process or event, in mathematical terms, a series of
formulas. Mathematical equations intended to describe the real world. There are many
reasons modellemeni use in solving a problem. As an example of determining the number
of fish in a river or the sea, the cost to apply experimental methods to find the solution of
the problem may be too high. How to move objects in an environment of zero gravity,
such as that they were not putting, would be impossible to apply the experimental
paths. In the real world of experimental difficulties in handling mathematical modeling to
predict how to act in any case where the systems referenced.
The difficulty of decision making in the emerging markets after the Second World
War, this area has led to the development of some techniques for. This technique is called
optimization techniques in general. Optimization techniques can be described as
optimization studies. These studies offer us the best of many variables, in terms of time
and cost savings can be achieved. Choices made among alternatives, not experience,
modified according to mathematical models provide a more healthy results. Numerical
methods of optimization techniques, linear programming is described as the first
technique developed in this regard. However, in reality the structure exhibits a non-linear
many problems have led to the development of many other techniques more.
Mathematical models are developed in harmony with real life problems arise over time,
have led researchers to examine patterns of life in nature.
Population-based techniques have emerged as a result of this orientation. These
techniques, birds, ants, bees, and so on.colonies and analyzed by these techniques have
various social simulation performed in many different areas. Particle Swarm Optimization
(PSO) technique is a population-based heuristic optimization technique. Simulation of
social behavior of flocks of birds or fish has been developed. Particle Swarm
Optimization and multivariate multi-parameter optimization technique is used to find
solutions to problems. Particle Swarm Optimization (PSO) technique as flocks of birds or
fish have been developed inspired by social behavior. Developed by examining the
behavior of individuals interacting with each other and the environment. This concept is
also called particle intelligence. PSO named as particle potential solutions, the best
solutions to the current problem space by following the surfing. PSO, function
optimization, scheduling, training neural networks, fuzzy logic systems, image
processing, portfolio optimization and so on. is widely used in many fields.
A specific area of the core logic of Particle Swarm Optimization, is just one region, food,
food in this area looking for a bird group, and initially did not know where the food is
accepted, the food and attempted to answer the question of what could be the best solution
to find.
Mind, that gets to the genetic path of love, fear, jealousy, as well as a natural defense
motives şartlandırmalarından current environment and the community received the
influence of interactions evolving.So the mind is not fixed, but can not increase until the
end of human life and is a skill that can develop. Mind, the machine, the computer
software, or otherwise can not be imitated
Particle Swarm Optimization and multivariate multi-parameter optimization technique
is used to find solutions to problems. PSO, such as genetic algorithms shows many
similarities with evolutionary computation techniques. The system starts a population
with random solutions and searches for optimum solutions by updating generations.
The notion of a social system is a simplified Particle Swarm square is simulated. The main goal is to make the simulation graphically, but the elegant choreography of a flock
of birds is unpredictable.Comparison of simulations combined with first rate close to the
neighborhood, the elimination of covariates and distance, accelerate research and changed
to a unified multi-dimensional. At a certain point in the evolution of algorithms, a
conceptual model was the difference, really, this one from the optimizer. From the
beginning to the end of a trial and error, a few parameters for the optimization algorithmto
eliminate the leaders of the secondary.
Herd brought together representatives from the term structure to refer to each other,
affecting the senses are used in general. Called because a flock of bees, but lots of lots of
classic example of expansion of the other systems of similar nature. A lot of an ant colony
where ants may be considered as individual representatives, where a bevy of birds of
representatives, a sürüdür cars in traffic, a crowded flock of humanity, a flock of immune
system cells and molecules, and the economy, representatives of the flock of the
economy. A flock of birds, although it is the concept of herd-like, space is recommended
in the opinion of joint action, and this relates to all common types of behavior, not related
to the spatial movement
Some of the genetic mechanisms that underlie such cooperation can be defined as: for
example, multi-shaped ant species, such as the difference between the larger and more
junior division of labor can conduct the anatomical differences between
individuals.However, many views on the joint activities of social insects is that the selforganizing.
In fact, in the context of physics and chemistry of macroscopic (large scale)
models, processes and interactions outside the self-organizing theory developed to
describe the emergence of a macroscopic level, the social insects, the complex
interactions between individuals can undermine the common behavior shows a simplebehaving.
In such cases there is no need to resort to complex social behavior to explain
the complexity of individual.
In 1952, Harry Markowitz's Modern Portfolio management is considered as the
beginning of the article published by Porfolio Selection. Only by diversifying its
portfolio, explains the importance of relationships between securities.Markowitz meanvariance
model, developed in 1956, restructured the Modern Portfolio theory. The
Markowitz theory by evaluating the past performances of the security's expected return
and aims to predict.
The general framework of the Modern Portfolio Theory founder, Harry Markowitz's
approach today, an investor-owned securities and to deposit a certain amount, the money
is to keep a term. This approach is based on a portfolio of securities selected by the
investor potential portfolios.
Commodities, gold, silver, copper, crude oil, natural gas, coal, wheat, cotton, corn,
sugar, coffee products, such as formed by nature to be the subject goods, the name given
to trade.Commodities are used to form a more valuable and different products, and the
values determined by the consumer, valuable, chemical products, emission products,
animal products and energy products. All of these products "commodity" is
called. Commodity products are natural disasters, crises, that may fluctuate due to
changes in seasonal products. These products generated by the portfolio optimization
techniques were used in order to manage effectively and efficiently.
Commodity products, economic, social and political changes affected. These changes
are sources of systematic risk. Capital market returns are affected by commodity price
movements in the general market risk, interest rate risk through its effect on commodity prices, changes in the level of inflation due to commodity inflation risk returns, systematic
risk variety, which lead to change.
Particle Swarm Optimization technique in this study by explaining the theoretical
structure of the commodity market with products made of portfolio optimization.
Particle Swarm Optimization technique used in this study, what conclusions can be set in
advance for portfolio optimization and interpretation of these results will be
provided. Particle Swarm Optimization technique and portfolio weights with the optimal
balance of risk and return will be achieved.
Abstract
Karar vermenin zorluğu ve matematiğin gelişimi, karmaşık sistemlerde en iyi çözüme ulaşmak için matematiksel uygulamaların ortaya çıkmasına neden olmuştur. Matematiksel uygulamalardan biri olan optimizasyon yönetim, ekonomi, planlama, mühendislik gibi birçok alanda en iyi çözümü sunan yöntemleri içermektedir. Parçacık Sürü Optimizasyonu (PSO) tekniği popülasyon temelli sezgisel bir optimizasyon tekniğidir. Kuş veya balık sürülerinin sosyal davranışlarının benzetimi ile geliştirilmiştir. Parçacık Sürü Optimizasyonu tekniği çok parametreli ve çok değişkenli optimizasyon problemlerine çözüm bulmak için kullanılmaktadır. Bu çalışmada da Parçacık Sürü Optimizasyon tekniğinin teorik yapısı anlatılarak emtia piyasası ürünleri ile portföy optimizasyonu yapılmıştır.
Details
| Other ID | JA99RR93BT |
|---|---|
| Journal Section | Articles |
| Authors | |
| Publication Date | June 1, 2012 |
| Submission Date | June 1, 2012 |
| Published in Issue | Year 2012 Volume: 12 Issue: 23 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.