Wolfgang Ketter

A Multi-Agent Negotiation Testbed for Contracting Tasks with Temporal and Precedence Constraints

In multi-agent contracting, customer agents solicit the resources and capabilities of other agents, sometimes executing multistep tasks in which tasks are contracted out to different suppliers. The authors have developed a testbed for studying the decision behaviors of agents in this context. It generates sets of tasks with known statistical attributes, formulates and submits requests for quotations, generates bids with well-defined statistics, and evaluates bids according to several criteria. Each of these processes is supported by an abstract interface and a series of pluggable modules with numerous configuration parameters, and with data collection and analysis tools.

Research Commentary---Designing Smart Markets

Electronic markets have been a core topic of information systems (IS) research for last three decades. We focus on a more recent phenomenon: smart markets. This phenomenon is starting to draw considerable interdisciplinary attention from the researchers in computer science, operations research, and economics communities. The objective of this commentary is to identify and outline fruitful research areas where IS researchers can provide valuable contributions. The idea of smart markets revolves around using theoretically supported computational tools to both understand the characteristics of complex trading environments and multiechelon markets and help human decision makers make real-time decisions in these complex environments. We outline the research opportunities for complex trading environments primarily from the perspective of design of computational tools to analyze individual market organization and provide decision support in these complex environments. In addition, we present broad research opportunities that computational platforms can provide, including implications for policy and regulatory research.

A reinforcement learning approach to autonomous decision-making in smart electricity markets

The vision of a Smart Electric Grid relies critically on substantial advances in intelligent decentralized control mechanisms. We propose a novel class of autonomous broker agents for retail electricity trading that can operate in a wide range of Smart Electricity Markets, and that are capable of deriving long-term, profit-maximizing policies. Our brokers use Reinforcement Learning with function approximation, they can accommodate arbitrary economic signals from their environments, and they learn efficiently over the large state spaces resulting from these signals. We show how feature selection and regularization can be leveraged to automatically optimize brokers for particular market conditions, and demonstrate the performance of our design in extensive experiments using real-world energy market data.

Detecting and forecasting economic regimes in multi-agent automated exchanges

We show how an autonomous agent can use observable market conditions to characterize the microeconomic situation of the market and predict market trends. The agent can use this information for tactical decisions, such as pricing, and strategic decisions, such as product mix and production planning. We present methods to learn dominant market conditions, such as over-supply or scarcity, from historical data using Gaussian mixture models. We show how this model combined with real-time observable information is used to identify the current dominant market condition and to forecast market changes over a planning horizon. Market changes are forecast via both a Markov correction-prediction process and an exponential smoother. Empirical analysis shows that the exponential smoother yields more accurate predictions for the current and next day (supporting tactical decisions), while the Markov process is better for longer term predictions (supporting strategic decisions). Our approach offers more flexibility than traditional regression based approaches, since it does not assume a fixed functional relationship between dependent and independent variables. We validate our methods by presenting experimental results in a case study, the Trading Agent Competition for Supply Chain Management.

Flexible decision control in an autonomous trading agent

Modern electronic commerce creates significant challenges for decision-makers. The trading agent competition for supply-chain management (TAC SCM) is an annual competition among fully-autonomous trading agents designed by teams around the world. Agents attempt to maximize profits in a supply-chain scenario that requires them to coordinate Procurement, Production, and Sales activities in competitive markets. An agent for TAC SCM is a complex piece of software that must operate in a competitive economic environment. We report on results of an informal survey of agent design approaches among the competitors in TAC SCM, and then we describe and evaluate the design of our MinneTAC trading agent. We focus on the use of evaluators - configurable, composable modules for data analysis, modeling, and prediction that are chained together at runtime to support agent decision-making. Through a set of examples, we show how this structure supports Sales and Procurement decisions, and how those decision process can be modified in useful ways by changing evaluator configurations.

Pushing the limits of rational agents: The trading agent competition for supply chain management

Over the years, competitions have been important catalysts for progress in Artificial Intelligence. We describe one such competition, the Trading Agent Competition for Supply Chain Management (TAC SCM). We discuss its significance in the context of today’s global market economy as well as AI research, the ways in which it breaks away from limiting assumptions made in prior work, and some of the advances it has engendered over the past six years. TAC SCM requires autonomous supply chain entities, modeled as agents, to coordinate their internal operations while concurrently trading in multiple dynamic and highly competitive markets. Since its introduction in 2003, the competition has attracted over 150 entries and brought together researchers from AI and beyond in the form of 75 competing teams from 25 different countries.

Flexible decision support in dynamic inter-organisational networks

An effective Decision Support System (DSS) should help its users improve decision making in complex, information-rich environments. We present a feature gap analysis that shows that current decision support technologies lack important qualities for a new generation of agile business models that require easy, temporary integration across organisational boundaries. We enumerate these qualities as DSS Desiderata, properties that can contribute both effectiveness and flexibility to users in such environments. To address this gap, we describe a new design approach that enables users to compose decision behaviours from separate, configurable components, and allows dynamic construction of analysis and modelling tools from small, single-purpose evaluator services. The result is what we call an ‘evaluator service network’ that can easily be configured to test hypotheses and analyse the impact of various choices for elements of decision processes. We have implemented and tested this design in an interactive version of the MinneTAC trading agent, an agent designed for the Trading Agent Competition for Supply Chain Management.

A predictive empirical model for pricing and resource allocation decisions

We present a semi-parametric model that describes pricing behaviors in a market environment, and we show how that model can be used to guide resource allocation and pricing decisions in an autonomous trading agent. We validate our model by presenting experimental results obtained in the Trading Agent Competition for Supply Chain Management.

Real-Time Tactical and Strategic Sales Management for Intelligent Agents Guided by Economic Regimes

We present a computational approach that autonomous software agents can adopt to make tactical decisions, such as product pricing, and strategic decisions, such as product mix and production planning, to maximize profit in markets with supply and demand uncertainties. Using a combination of machine learning and optimization techniques, the agent is able to characterize economic regimes, which are historical microeconomic conditions reflecting situations such as over-supply and scarcity. We assume an agent is capable of using real-time observable information to identify the current dominant market condition and we show how it can forecast regime changes over a planning horizon. We demonstrate how the agent can then use regime characterization to predict prices, price trends, and the probability of receiving a customer order in a dynamic supply chain environment. We validate our methods by presenting experimental results from a testbed derived from the Trading Agent Competition for Supply Chain Management (TAC SCM). The results show that our agent outperforms traditional short- and long-term predictive methodologies (such as exponential smoothing) significantly, resulting in accurate prediction of customer order probabilities, and competitive market prices. This, in turn, has the potential to produce higher profits. We also demonstrate the versatility of our computational approach by applying the methodology to prediction of stock price trends.

MinneTAC Sales Strategies for Supply Chain TAC

We describe two sales strategies used by our agent, MinneTAC, for the 2003 Supply Chain Management Trading Agent Competition (TAC SCM). Both strategies estimate, as the game progresses, the probability of receiving a customer order for different prices and compute the expected profit. We empirically analyze the effect of the discount given by suppliers on orders made the first day of the game, and show that in high-demand games there is a strong correlation between the performance of an agent in the game and the offers it receives from suppliers the first day of the game.