• Sorted by Date • Classified by Publication Type • Classified by Research Category •
Wolfgang Ketter. Identification and Prediction of Economic Regimes to Guide Decision Making in Multi-Agent Marketplaces. In PhD Thesis, pp. 1–138, University of Minnesota, Twin-Cities, USA, January 2007.
Supply chain management is commonly employed by businesses toimprove organizational processes by optimizing the transfer ofgoods, information, and services between buyers and suppliers.Traditionally, supply chains have been created and maintainedthrough the interactions of human representatives of the variouscompanies involved. However, the recent advent of autonomoussoftware agents opens new possibilities for automating andcoordinating the decision making processes between the variousparties involved.Autonomous agents participating in supply chain management musttypically make their decisions in environments of high complexity,high variability, and high uncertainty since only limited informationis visible.We present an approach whereby an autonomous agent is able to maketactical decisions, such as product pricing, as well as strategicdecisions, such as product mix and production planning, in orderto maximize its profit despite the uncertainties in the market.The agent predicts future market conditions and adapts its decisionson procurement, production, and sales accordingly.Using a combination of machine learning and optimization techniques,the agent first characterizes the microeconomic conditions, suchas over-supply or scarcity, of the market. These conditions aredistinguishable statistical patterns that we call economicregimes. They are learned from historical data by using a GaussianMixture Model to model the price density of the different productsand by clustering price distributions that recur across days.In real-time the agent identifies the current dominant marketcondition and forecasts market changes over a planning horizon.Methods for the identification of regimes are explored in detail,and three different algorithms are presented. One is based onexponential smoothing, the second on a Markov prediction process,and the third on a Markov correction-prediction process. We examinea wide range of tuning options for these algorithms, and show howthey can be used to predict prices, price trends, and the probabilityof receiving a customer order.We validate our methods by presenting experimental results from theTrading Agent Competition for Supply Chain Management, an internationalcompetition of software agents that has provided inspiration for thiswork. We also show how the same approach can be applied to the stockmarket.
@InProceedings{KetterPhDThesis,
author = "Wolfgang Ketter",
title = "Identification and Prediction of Economic Regimes to
Guide Decision Making in Multi-Agent Marketplaces",
booktitle = "PhD Thesis",
pages = {1--138},
year = "2007",
abstract = "Supply chain management is commonly employed by businesses to
improve organizational processes by optimizing the transfer of
goods, information, and services between buyers and suppliers.
Traditionally, supply chains have been created and maintained
through the interactions of human representatives of the various
companies involved. However, the recent advent of autonomous
software agents opens new possibilities for automating and
coordinating the decision making processes between the various
parties involved.
Autonomous agents participating in supply chain management must
typically make their decisions in environments of high complexity,
high variability, and high uncertainty since only limited information
is visible.
We present an approach whereby an autonomous agent is able to make
tactical decisions, such as product pricing, as well as strategic
decisions, such as product mix and production planning, in order
to maximize its profit despite the uncertainties in the market.
The agent predicts future market conditions and adapts its decisions
on procurement, production, and sales accordingly.
Using a combination of machine learning and optimization techniques,
the agent first characterizes the microeconomic conditions, such
as over-supply or scarcity, of the market. These conditions are
distinguishable statistical patterns that we call \emph{economic
regimes}. They are learned from historical data by using a Gaussian
Mixture Model to model the price density of the different products
and by clustering price distributions that recur across days.
In real-time the agent identifies the current dominant market
condition and forecasts market changes over a planning horizon.
Methods for the identification of regimes are explored in detail,
and three different algorithms are presented. One is based on
exponential smoothing, the second on a Markov prediction process,
and the third on a Markov correction-prediction process. We examine
a wide range of tuning options for these algorithms, and show how
they can be used to predict prices, price trends, and the probability
of receiving a customer order.
We validate our methods by presenting experimental results from the
Trading Agent Competition for Supply Chain Management, an international
competition of software agents that has provided inspiration for this
work. We also show how the same approach can be applied to the stock
market.",
address = {University of Minnesota, Twin-Cities, USA},
month = {January},
bib2html_pubtype = {Thesis},
bib2html_rescat = {Trading Agents: Supply-Chain Management},
}
Generated by bib2html.pl (written by Patrick Riley ) on Tue Jun 24, 2008 02:42:47