Michael A. H. Dempster

A real-time adaptive trading system using genetic programming

Technical analysis indicators are widely used by traders in financial and commodity markets to predict future price levels and enhance trading profitability. We have previously shown a number of popular indicator-based trading rules to be loss-making when applied individually in a systematic manner. However, technical traders typically use combinations of a broad range of technical indicators. Moreover, successful traders tend to adapt to market conditions by dropping trading rules as soon as they become loss-making or when more profitable rules are found. In this paper we try to emulate such traders by developing a trading system consisting of rules based on combinations of different indicators at different frequencies and lags. An initial portfolio of such rules is selected by a genetic algorithm applied to a number of indicators calculated on a set of US Dollar/British Pound spot foreign exchange tick data from 1994 to 1997 aggregated to various intraday frequencies. The genetic algorithm is subsequently used at regular intervals on out-of-sample data to provide new rules and a feedback system is utilized to rebalance the rule portfolio, thus creating two levels of adaptivity. Despite the individual indicators being generally loss-making over the data period, the best rule found by the developed system is found to be modestly, but significantly, profitable in the presence of realistic transaction costs.

Computational learning techniques for intraday FX trading using popular technical indicators

We consider strategies which use a collection of popular technical indicators as input and seek a profitable trading rule defined in terms of them. We consider two popular computational learning approaches, reinforcement learning and genetic programming, and compare them to a pair of simpler methods: the exact solution of an appropriate Markov decision problem, and a simple heuristic. We find that although all methods are able to generate significant in-sample and out-of-sample profits when transaction costs are zero, the genetic algorithm approach is superior for non-zero transaction costs, although none of the methods produce significant profits at realistic transaction costs. We also find that there is a substantial danger of overfitting if in-sample learning is not constrained.

Spread Option Valuation and the Fast Fourier Transform

We investigate a method for pricing the generic spread option beyond the classical two-factor Black-Scholes framework by extending the fast Fourier Transform technique introduced by Carr & Madan (1999) to a multi-factor setting. The method is applicable to models in which the joint characteristic function of the prices of the underlying assets forming the spread is known analytically. This enables us to incorporate stochasticity in the volatility and correlation structure — a focus of concern for energy option traders — by introducing additional factors within an affine jump-diffusion framework. Furthermore, computational time does not increase significantly as additional random factors are introduced, since the fast Fourier Transform remains two dimensional in terms of the two prices defining the spread. This yields considerable advantage over Monte Carlo and PDE methods and numerical results are presented to this effect.

Analytical Evaluation of Hierarchical Planning Systems

Hierarchical planning systems have become popular for multilevel decision problems. After reviewing the concept of hierarchical planning and citing some examples, we describe a method for analytic evaluation of a hierarchical planning system. We show that multilevel decision problems can be nicely modeled as multistage stochastic programs. Then any hierarchical planning system can be measured against the yardstick of optimality in this stochastic program. We demonstrate this approach on a hierarchical system that can be shown to be asymptotically optimal for a job shop design/scheduling problem.

GLOBAL ASSET LIABILITY MANAGEMENT

Dynamic financial analysis (DFA) is a technique which uses Monte Carlo simulation to investigate the evolution over time of financial models of funds, complex liabilities and entire firms. Although of increasing popularity, the drawback of DFA is the dearth of systematic methods for optimising model parameters for strategic financial planning. This paper introduces strategic DFA which employs the only recently mature technology of dynamic stochastic optimisation to fill this gap. The new approach is described in terms of an illustrative case study of a joint university/industry project to create a decision support system for strategic asset liability management involving global asset classes and defined contribution pension plans. Although the application of the system described in the paper is to fund design and risk management, the approach and techniques described here are much more broadly applicable to strategic financial planning problems; for example, to insurance and reinsurance firms, to risk capital allocation in financial institutions and trading firms and to corporate investment and business development involving real options. As well as describing the mathematical and statistical models used in the case study, the paper treats econometric estimation, asset return and liability scenario generation, model specification and optimisation, system evaluation and historical backtesting. Throughout the system visualisation plays an important role.

Adaptive systems for foreign exchange trading

Foreign exchange markets are notoriously difficult to predict. For many years academics and practitioners alike have tried to build trading models, but history has not been kind to their efforts. Consistently predicting FX markets has seemed like an impossible goal but recent advances in financial research now suggest otherwise. With newly developed computational techniques and newly available data, the development of successful trading models is looking possible. The Centre for Financial Research (CFR) at Cambridge University’s Judge Institute of Management has been researching trading techniques in foreign exchange markets for a number of years. Over the last 18 months a joint project with HSBC Global Markets has looked at how the bank’s proprietary information on customer order flow and on the customer limit order book can be used to enhance the profitability of technical trading systems in FX markets. Here we give an overview of that research and report our results.

A financial expert decision support system

Corporate management decisions require domain knowledge, analytical skills and expert judgment for decision making in an uncertain environment. These decisions are often made with the help of decision support systems, which provide automated computation and data analysis but rely on knowledgeable users or consultants to direct the system operations and interpret results. Expert systems technology, by modelling the knowledge and reasoning of human experts, offers the opportunity to incorporate model management and interpretation knowledge within decision support systems. Such systems can make complex modelling techniques directly accessible to non-expert users.

Exponential Growth of Fixed-Mix Strategies in Stationary Asset Markets

Abstract. The paper analyzes the long-run performance of dynamic investment strategies based on fixed-mix portfolio rules. Such rules prescribe rebalancing the portfolio by transferring funds between its positions according to fixed (time-independent) proportions. The focus is on asset markets where prices fluctuate as stationary stochastic processes. Under very general assumptions, it is shown that any fixed-mix strategy in a stationary market yields exponential growth of the portfolio with probability one.

Designing Minimum Guaranteed Return Funds

In recent years there has been a significant growth of investment products aimed at attracting investors who are worried about the downside potential of the financial markets. This paper introduces a dynamic stochastic optimization model for the design of such products. The pricing of minimum guarantees as well as the valuation of a portfolio of bonds based on a three-factor term structure model are described in detail. This allows us to accurately price individual bonds, including the zero-coupon bonds used to provide risk management, rather than having to rely on a generalized bond index model.

Volatility-induced financial growth

We show that the volatility of a price process, which is usually regarded as an impediment to financial growth, can serve as an endogenous factor in its acceleration.