Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes

Alexander Hogenboom, Wolfgang Ketter, Jan van Dalen, Uzay Kaymak, John Collins, Alok Gupta

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In today's complex and dynamic supply chain markets, information systems are essential for effective supply chain management. Complex decision making processes on strategic, tactical, and operational levels require substantial timely support in order to contribute to organizations' agility. Consequently, there is a need for sophisticated dynamic product pricing mechanisms that can adapt quickly to changing market conditions and competitors' strategies. We propose a two-layered machine learning approach to compute tactical pricing decisions in real time. The first layer estimates prevailing economic conditions-economic regimes-identifying and predicting current and future market conditions. In the second layer, we train a neural network for each regime to estimate price distributions in real time using available information. The neural networks compute offer acceptance probabilities from a tactical perspective to meet desired sales quotas. We validate our approach in the trading agent competition for supply chain management. When competing against the world's leading agents, the performance of our system significantly improves compared to using only economic regimes to predict prices. Profits increase significantly even though the prices and sales volume do not change significantly. Instead, tactical pricing results in a more efficient sales strategy by reducing both finished goods and components inventory costs.

Original languageEnglish (US)
Pages (from-to)791-818
Number of pages28
JournalDecision Sciences
Volume46
Issue number4
DOIs
StatePublished - Aug 1 2015

Fingerprint

Supply chains
Sales
Economics
Supply chain management
Costs
Neural networks
Learning systems
Profitability
Information systems
Decision making
Pricing
Supply chain
Market conditions
Market information
Economic conditions
Pricing mechanism
Competitors
Profit
Supply chain dynamics
Agility

Keywords

  • Auctions
  • Dynamic Pricing
  • Economic Regimes
  • Multi-agent systems
  • Supply Chain Management

Cite this

Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes. / Hogenboom, Alexander; Ketter, Wolfgang; van Dalen, Jan; Kaymak, Uzay; Collins, John; Gupta, Alok.

In: Decision Sciences, Vol. 46, No. 4, 01.08.2015, p. 791-818.

Research output: Contribution to journalArticle

Hogenboom, A, Ketter, W, van Dalen, J, Kaymak, U, Collins, J & Gupta, A 2015, 'Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes', Decision Sciences, vol. 46, no. 4, pp. 791-818. https://doi.org/10.1111/deci.12146
Hogenboom, Alexander ; Ketter, Wolfgang ; van Dalen, Jan ; Kaymak, Uzay ; Collins, John ; Gupta, Alok. / Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes. In: Decision Sciences. 2015 ; Vol. 46, No. 4. pp. 791-818.
@article{50e541cd9511451480ba35aaf032d902,
title = "Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes",
abstract = "In today's complex and dynamic supply chain markets, information systems are essential for effective supply chain management. Complex decision making processes on strategic, tactical, and operational levels require substantial timely support in order to contribute to organizations' agility. Consequently, there is a need for sophisticated dynamic product pricing mechanisms that can adapt quickly to changing market conditions and competitors' strategies. We propose a two-layered machine learning approach to compute tactical pricing decisions in real time. The first layer estimates prevailing economic conditions-economic regimes-identifying and predicting current and future market conditions. In the second layer, we train a neural network for each regime to estimate price distributions in real time using available information. The neural networks compute offer acceptance probabilities from a tactical perspective to meet desired sales quotas. We validate our approach in the trading agent competition for supply chain management. When competing against the world's leading agents, the performance of our system significantly improves compared to using only economic regimes to predict prices. Profits increase significantly even though the prices and sales volume do not change significantly. Instead, tactical pricing results in a more efficient sales strategy by reducing both finished goods and components inventory costs.",
keywords = "Auctions, Dynamic Pricing, Economic Regimes, Multi-agent systems, Supply Chain Management",
author = "Alexander Hogenboom and Wolfgang Ketter and {van Dalen}, Jan and Uzay Kaymak and John Collins and Alok Gupta",
year = "2015",
month = "8",
day = "1",
doi = "10.1111/deci.12146",
language = "English (US)",
volume = "46",
pages = "791--818",
journal = "Decision Sciences",
issn = "0011-7315",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Adaptive Tactical Pricing in Multi-Agent Supply Chain Markets Using Economic Regimes

AU - Hogenboom, Alexander

AU - Ketter, Wolfgang

AU - van Dalen, Jan

AU - Kaymak, Uzay

AU - Collins, John

AU - Gupta, Alok

PY - 2015/8/1

Y1 - 2015/8/1

N2 - In today's complex and dynamic supply chain markets, information systems are essential for effective supply chain management. Complex decision making processes on strategic, tactical, and operational levels require substantial timely support in order to contribute to organizations' agility. Consequently, there is a need for sophisticated dynamic product pricing mechanisms that can adapt quickly to changing market conditions and competitors' strategies. We propose a two-layered machine learning approach to compute tactical pricing decisions in real time. The first layer estimates prevailing economic conditions-economic regimes-identifying and predicting current and future market conditions. In the second layer, we train a neural network for each regime to estimate price distributions in real time using available information. The neural networks compute offer acceptance probabilities from a tactical perspective to meet desired sales quotas. We validate our approach in the trading agent competition for supply chain management. When competing against the world's leading agents, the performance of our system significantly improves compared to using only economic regimes to predict prices. Profits increase significantly even though the prices and sales volume do not change significantly. Instead, tactical pricing results in a more efficient sales strategy by reducing both finished goods and components inventory costs.

AB - In today's complex and dynamic supply chain markets, information systems are essential for effective supply chain management. Complex decision making processes on strategic, tactical, and operational levels require substantial timely support in order to contribute to organizations' agility. Consequently, there is a need for sophisticated dynamic product pricing mechanisms that can adapt quickly to changing market conditions and competitors' strategies. We propose a two-layered machine learning approach to compute tactical pricing decisions in real time. The first layer estimates prevailing economic conditions-economic regimes-identifying and predicting current and future market conditions. In the second layer, we train a neural network for each regime to estimate price distributions in real time using available information. The neural networks compute offer acceptance probabilities from a tactical perspective to meet desired sales quotas. We validate our approach in the trading agent competition for supply chain management. When competing against the world's leading agents, the performance of our system significantly improves compared to using only economic regimes to predict prices. Profits increase significantly even though the prices and sales volume do not change significantly. Instead, tactical pricing results in a more efficient sales strategy by reducing both finished goods and components inventory costs.

KW - Auctions

KW - Dynamic Pricing

KW - Economic Regimes

KW - Multi-agent systems

KW - Supply Chain Management

UR - http://www.scopus.com/inward/record.url?scp=84940453538&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940453538&partnerID=8YFLogxK

U2 - 10.1111/deci.12146

DO - 10.1111/deci.12146

M3 - Article

VL - 46

SP - 791

EP - 818

JO - Decision Sciences

JF - Decision Sciences

SN - 0011-7315

IS - 4

ER -