In the context of a dynamic trading strategy, the ultimate purpose of any forecasting model is to choose actions which result in the optimisation of the trading objective. In this paper we develop a methodology for optimising an objective function, using a parameterised decision rule, for a given forecasting model. We simulate the expected trading performance for different decision parameters a...

This work describes a multi-agent architecture and strategy for trade in simultaneous and related auctions. The proposed SIMPLE Agency combines an integer programming model, machine learning techniques and knowledge engineering strategies to build its decision making process. Some well known problems in trading were identified in order to design the architecture. Each SIMPLE agent is concerned ...

We describe UCFTAC, a trading agent based on control based principles, which has participated with success in 2006 Supply Chain Management Trading Agent Competition. The UCFTAC approach uses a sophisticated procurement strategy and an aggressive price control feature. It achieved competitive results in the TAC-SCM 2006 qualification round. Our design consists of a loosely coupled set of agent-m...

In this paper we present a methodology that guides the development of a multiagent system for trading in electronic markets. Our approach uses a strategy of decomposing a complex trading problem into sub-problems, and defines agent roles that tackle these sub-problems. We also present an incremental development process for building asynchronous and distributed agents, which enable effortlessly ...

A stock market is a highly complex dynamical system. Stock-price movements are not solely driven by fundamental values but in particular influenced by short term trading behaviour. Chartists use trends to forecast future price directions, whereas fundamentalists estimate stock prices based on dividend payouts or company earnings. Such strategies can similarly be deployed in automatic trading ag...

The Trading Agent Competition (TAC) is an annual event in which teams from around the world compete in a given scenario concerning the trading agent problem. This paper describes some of the key features and strategies employed by HarTAC, the Harvard University TAC SCM 2003 agent. HarTAC was built to be a moderately aggressive, production-oriented agent, combining a semi-conservative component ...

Given the return series for a set of instruments, a trading strategy is a switching function that transfers wealth from one instrument to another at specified times. We present efficient algorithms for constructing (ex-post) trading strategies that are optimal with respect to the total return, the Sterling ratio and the Sharpe ratio. Such optimal strategies are useful as benchmarks, and for ide...