- +44 (0)7974 145461
Research Interests:
The specific purpose of this paper is to investigate the empirical evidence of stock price anomalies, especially day-of-the-week, month-of-the-year and the holiday effect. The review covers the critical evaluation of calendar anomalies,... more
The specific purpose of this paper is to investigate the empirical evidence of stock price anomalies, especially day-of-the-week, month-of-the-year and the holiday effect. The review covers the critical evaluation of calendar anomalies, and the major focus has been given to extensively cited papers. Most of the researchers have found evidence of a negative Monday effect, though a relatively small number of researchers have refuted these results. We found a clear indication of a January effect in developed stock markets; however, there was no consensus in developing and least developed countries. Most of the researchers found a strong pre-holiday effect in the majority of markets; however, a few researchers found that the pre-holiday effect has diminished. The research could be extended to include other calendar anomalies such as the turn-of-the-month effect and semi-month effect. This research is helpful to all stakeholders of the stock market, specifically to regulators for maintaining market efficiency.
Research Interests:
Independent component analysis (ICA) is a computational method from statistics and signal processing which is a special case of blind source separation. ICA seeks to separate a multivariate signal into additive subcomponents supposing the... more
Independent component analysis (ICA) is a computational method from statistics and signal processing which is a special case of blind source separation. ICA seeks to separate a multivariate signal into additive subcomponents supposing the mutual statistical independence of the non-Gaussian source signals. The general framework of ICA was introduced in the early 1980s (Hérault and Ans 1984; Ans, Hérault and Jutten 1985; Hérault, Jutten and Ans 1985), but was most clearly stated by Pierre Comon in 1994 (Comon 1994 ...
Research Interests:
• As part of Shellenberger, et al.(1999)'s report into day trading, randomly selected short-term trading accounts which existed within the period 1997–1998 were analyzed. Seventy percent of the accounts lost money and were traded in... more
• As part of Shellenberger, et al.(1999)'s report into day trading, randomly selected short-term trading accounts which existed within the period 1997–1998 were analyzed. Seventy percent of the accounts lost money and were traded in a manner that realized a 100% risk of ruin (loss of all funds), whilst only 11.5% of the accounts reviewed evidenced the ability to conduct profitable short-term trading.
Human-induced climate change is a classic case of Garrett Hardin's tragedy of the commonsthe benefits of burning fossil fuels accrue to individuals, companies and nations, whilst the costs accrue to the planet as a whole. The... more
Human-induced climate change is a classic case of Garrett Hardin's tragedy of the commonsthe benefits of burning fossil fuels accrue to individuals, companies and nations, whilst the costs accrue to the planet as a whole. The tragedy of the commons is a multi-...
Abstract This article takes the form of a research proposal. The paper seeks to address the problem faced by investors of how best to deal with decision making under risk. The methodology utilizes a normative model from economics—expected... more
Abstract This article takes the form of a research proposal. The paper seeks to address the problem faced by investors of how best to deal with decision making under risk. The methodology utilizes a normative model from economics—expected utility theory—and a descriptive model from psychology—prospect theory—to formulate a rational but realistic compromise between the two: a prescriptive model of risk preferences.
VC dimension (for Vapnik Chervonenkis dimension) measures the capacity of a hypothesis space. Capacity is a measure of complexity and measures the expressive power, richness or flexibility of a set of functions by assessing how wiggly its... more
VC dimension (for Vapnik Chervonenkis dimension) measures the capacity of a hypothesis space. Capacity is a measure of complexity and measures the expressive power, richness or flexibility of a set of functions by assessing how wiggly its members can be. The definitions below are taken from Vapnik (1999).
The idea of ensemble learning is to employ multiple learners and combine their predictions. There is no definitive taxonomy. Jain, Duin and Mao (2000) list eighteen classifier combination schemes; Witten and Frank (2000) detail four... more
The idea of ensemble learning is to employ multiple learners and combine their predictions. There is no definitive taxonomy. Jain, Duin and Mao (2000) list eighteen classifier combination schemes; Witten and Frank (2000) detail four methods of combining multiple models: bagging, boosting, stacking and errorcorrecting output codes whilst Alpaydin (2004) covers seven methods of combining multiple learners: voting, error-correcting output codes, bagging, boosting, mixtures of experts, stacked generalization and cascading.
Over the past fifty years Bayesian inference has become the dominant theory of scientific method. This presentation argues not only that the Bayesian paradigm represents a credible scientific method, but that science essentially is... more
Over the past fifty years Bayesian inference has become the dominant theory of scientific method. This presentation argues not only that the Bayesian paradigm represents a credible scientific method, but that science essentially is applied Bayesian analysis. More precisely, science is intelligent applied subjective Bayesian analysis constrained by exchangeability, the Reflection Principle and the Principal Principle. ... To finish, the presentation shows that induction and abduction are in essence scientific, whilst Popper's falsification is not.
Market microstructure is a branch of economics and finance concerned with the details of how exchange occurs in markets, most commonly financial markets. Market microstructure research typically examines the ways in which the working... more
Market microstructure is a branch of economics and finance concerned with the details of how exchange occurs in markets, most commonly financial markets. Market microstructure research typically examines the ways in which the working process of a market affects trading costs, prices, volume and trading behaviour.
Abstract A market is said to be efficient with respect to an information set if the price 'fully reflects' that information set, ie if the price would be unaffected by revealing the information set to all market participants. The... more
Abstract A market is said to be efficient with respect to an information set if the price 'fully reflects' that information set, ie if the price would be unaffected by revealing the information set to all market participants. The efficient market hypothesis (EMH) asserts that financial markets are efficient. On the one hand, the definitional 'fully'is an exacting requirement, suggesting that no real market could ever be efficient, implying that the EMH is almost certainly false.
Abstract The basic idea behind the Fisher kernel method is to train a (generative) hidden Markov model (HMM) on data to derive a Fisher kernel for a (discriminative) support vector machine (SVM). The Fisher kernel gives a... more
Abstract The basic idea behind the Fisher kernel method is to train a (generative) hidden Markov model (HMM) on data to derive a Fisher kernel for a (discriminative) support vector machine (SVM). The Fisher kernel gives a 'natural'similarity measure that takes into account the underlying probability distribution. If each data item is a (possibly varying length) sequence, each may be used to train a HMM, with the average of the models in the training set used to construct a global HMM.
Abstract This note presents a chronological review of the literature on ensemble learning which has accumulated over the past twenty years. The idea of ensemble learning is to employ multiple learners and combine their predictions. If we... more
Abstract This note presents a chronological review of the literature on ensemble learning which has accumulated over the past twenty years. The idea of ensemble learning is to employ multiple learners and combine their predictions. If we have a committee of M models with uncorrelated errors, simply by averaging them the average error of a model can be reduced by a factor of M.
Feature selection (also known as subset selection) is a process commonly used in machine learning, wherein a subset of the features available from the data are selected for application of a learning algorithm. The best subset contains the... more
Feature selection (also known as subset selection) is a process commonly used in machine learning, wherein a subset of the features available from the data are selected for application of a learning algorithm. The best subset contains the least number of dimensions that most contribute to accuracy; we discard the remaining, unimportant dimensions. This is an important stage of preprocessing and is one of two ways of avoiding the curse of dimensionality (the other is feature extraction).
Abstract This note is best described as a'Research Challenge', and concerns building an ultra high frequency (UHF) trading system. The emphasis is on addressing the problems posed by UHF data, with a few thoughts on strategy and... more
Abstract This note is best described as a'Research Challenge', and concerns building an ultra high frequency (UHF) trading system. The emphasis is on addressing the problems posed by UHF data, with a few thoughts on strategy and implementation. The problem may be amenable to evolutionary computation.
Behavioural finance is the study of the influence of psychology on the behaviour of financial practitioners and the subsequent effect on markets. Behavioural finance helps explain why and how markets might be inefficient. For more... more
Behavioural finance is the study of the influence of psychology on the behaviour of financial practitioners and the subsequent effect on markets. Behavioural finance helps explain why and how markets might be inefficient. For more information on behavioural finance, see Sewell (2001).
Abstract Stock selection for hedge fund portfolios is a challenging problem that has previously been tackled by many machine-learning, genetic and evolutionary systems, including both Genetic Programming (GP) and Support Vector Machines... more
Abstract Stock selection for hedge fund portfolios is a challenging problem that has previously been tackled by many machine-learning, genetic and evolutionary systems, including both Genetic Programming (GP) and Support Vector Machines (SVM). But which is the better?
The term kernel is derived from a word that can be traced back to c. 1000 and originally meant a seed (contained within a fruit) or the softer (usually edible) part contained within the hard shell of a nut or stone-fruit. The former... more
The term kernel is derived from a word that can be traced back to c. 1000 and originally meant a seed (contained within a fruit) or the softer (usually edible) part contained within the hard shell of a nut or stone-fruit. The former meaning is now obsolete. It was first used in mathematics when it was defined for integral equations in which the kernel is known and the other function (s) unknown, but now has several meanings in maths. The machine learning term kernel trick was first used in 1998.
Abstract This note reviews the literature on fund performance. A practical way of gauging market efficiency is to attempt to identify above-average risk-adjusted returns from one or more market participants that are the result of skill,... more
Abstract This note reviews the literature on fund performance. A practical way of gauging market efficiency is to attempt to identify above-average risk-adjusted returns from one or more market participants that are the result of skill, as opposed to luck. If any such returns are identified, then the market is not efficient. In practice, such a test is best performed by seeking persistence in the returns of fund managers; if persistence is identified, then markets are not efficient.
Abstract The efficient market hypothesis (EMH) has been the central proposition of finance since the early 1970s and is one of the most well-studied hypotheses in all the social sciences, yet, surprisingly, there is still no consensus,... more
Abstract The efficient market hypothesis (EMH) has been the central proposition of finance since the early 1970s and is one of the most well-studied hypotheses in all the social sciences, yet, surprisingly, there is still no consensus, even among financial economists, as to whether the EMH holds. Five statistical analyses are conducted in an attempt to explicate such apparently contrary convictions.
Abstract This note outlines a general framework for conducting policy-relevant science. I argue that science is essentially applied subjective Bayesian inference, and that putting a probability on a hypothesis is necessary, but sometimes... more
Abstract This note outlines a general framework for conducting policy-relevant science. I argue that science is essentially applied subjective Bayesian inference, and that putting a probability on a hypothesis is necessary, but sometimes difficult. An effective policy should accommodate our innate degree of altruism. For example, individuals are motivated to invest something like 3% of their resources into humanity as a whole, which has implications for international policy.
Science is the systematic study of the universe—through observation and experiment—in the pursuit of knowledge that allows us to generalize. Although considered bad form in the current climate of political correctness (Lind 1998, 2004;... more
Science is the systematic study of the universe—through observation and experiment—in the pursuit of knowledge that allows us to generalize. Although considered bad form in the current climate of political correctness (Lind 1998, 2004; Ellis 2004; Browne 2006; Sewell 2007b), the ability to generalize is a distilled version of what science is all about.
Genetic programming (GP) is an evolutionary algorithm that optimizes a population of computer programs according to a fitness landscape determined by a program's ability to perform a user-defined task. The first experiments with GP were... more
Genetic programming (GP) is an evolutionary algorithm that optimizes a population of computer programs according to a fitness landscape determined by a program's ability to perform a user-defined task. The first experiments with GP were reported by Smith (1980) and Cramer (1985), and the seminal book is Koza (1992).
Research which asserts that there is a difference in male and female intelligence causes as much of a stir as that which shows the differences in race IQs. However, it is the differences in intelligence of the sexes which is far more... more
Research which asserts that there is a difference in male and female intelligence causes as much of a stir as that which shows the differences in race IQs. However, it is the differences in intelligence of the sexes which is far more controversial among experts, with approximately half of the studies finding no difference, and half finding a small male advantage. A meta-study of 26 articles that measure male and female IQ (see table below) was performed.
• Bollerslev and Domowitz (1993) used computer simulations to study the effects of varying the length of an electronic order book. They state that the appearance and increasing persistence of serial correlation in the variance of... more
• Bollerslev and Domowitz (1993) used computer simulations to study the effects of varying the length of an electronic order book. They state that the appearance and increasing persistence of serial correlation in the variance of transactions price returns is traced to the existence and length of the electronic book, as is the degree of non-normality in transactions returns.
Chaos has a precise meaning within the world of physics and non-linear mathematics, but applications of 'chaos theory' in other domains (in management, for example) are generally bogus. Mathematical definitions of chaos vary, what follows... more
Chaos has a precise meaning within the world of physics and non-linear mathematics, but applications of 'chaos theory' in other domains (in management, for example) are generally bogus. Mathematical definitions of chaos vary, what follows is an informal one. Chaos exists when a deterministic dynamical system is sensitive to initial conditions and gives rise to effectively unpredictable long-term behaviour. Note that high dimensional chaos is indistinguishable from a stochastic process, we're interested in whether markets exhibit low-dimensional chaos.
Abstract Many philosophies treat emotions as the polar opposite of logic, and an economist would judge emotions as irrational. Taking an evolutionary perspective informs us that emotion is no less rational than any other behaviour, and... more
Abstract Many philosophies treat emotions as the polar opposite of logic, and an economist would judge emotions as irrational. Taking an evolutionary perspective informs us that emotion is no less rational than any other behaviour, and likely evolved to maximize lifetime utility. Frank (1988) argues that emotions evolved to enable us to sacrifice a short-term benefit for a longer-term gain. Frank's work is interpreted via a bottom-up evolutionary approach within the framework of the prisoner's dilemma.
A hidden Markov model (HMM) is a temporal probabilistic model in which the state of the process is described by a single discrete random variable. Loosely speaking, it is a Markov chain observed in noise. The theory of hidden Markov... more
A hidden Markov model (HMM) is a temporal probabilistic model in which the state of the process is described by a single discrete random variable. Loosely speaking, it is a Markov chain observed in noise. The theory of hidden Markov models was developed in the late 1960s and early 1970s by Baum, Eagon, Petrie, Soules and Weiss (Baum and Petrie 1966; Baum and Eagon 1967; Baum, et al. 1970; Baum 1972), whilst the name 'hidden Markov model'was coined by LP Neuwirth.
Abstract For a speculative investor, there are two aspects to optimizing a trading strategy. The first and most important goal of a trader is to achieve a positive expected risk-adjusted return. Once this has been achieved, the trader... more
Abstract For a speculative investor, there are two aspects to optimizing a trading strategy. The first and most important goal of a trader is to achieve a positive expected risk-adjusted return. Once this has been achieved, the trader needs to know what percentage of his capital to risk on each trade. Within the trading fraternity this task is often know as money management. The underlying principals of money management apply to both gambling and trading, and were originally developed for the former.
Abstract This paper provides an exhaustive review of the literature on the characterization of financial time series. A stylized fact is a term in economics used to refer to empirical findings that are so consistent across markets that... more
Abstract This paper provides an exhaustive review of the literature on the characterization of financial time series. A stylized fact is a term in economics used to refer to empirical findings that are so consistent across markets that they are accepted as truth. Financial time series may be characterized by the following stylized facts. The autocorrelation of returns is largely insignificant.