Genetic algorithms and investment strategies: A global perspective

The profitability of momentum portfolios in the equity markets is derived from the continuation of stock returns over medium time horizons. The empirical evidence of momentum, however, is significantly different across markets around the world. The purpose of this dissertation is to: (1) help global investors determine the optimal selection and holding periods for momentum portfolios, (2) evaluate the profitability of the optimized momentum portfolios in different time periods and market states, (3) assess the investment strategy profits after considering transaction costs, and (4) interpret momentum returns within the framework of prior studies on investors’ behavior. Improving on the traditional practice of selecting arbitrary selection and holding periods, a genetic algorithm (GA) is employed. The GA performs a thorough and structured search to capture the return continuations and reversals patterns of momentum portfolios. Three portfolio formation methods are used: price momentum, earnings momentum, and earnings and price momentum and a non-linear optimization procedure (GA). The focus is on common equity of the U.S. and a select number of countries, including Australia, France, Germany, Japan, the Netherlands, Sweden, Switzerland and the United Kingdom. The findings suggest that the evolutionary algorithm increases the annualized profits of the U.S. momentum portfolios. However, the difference in mean returns is statistically significant only in certain cases. In addition, after considering transaction costs, both price and earnings and price momentum portfolios do not appear to generate abnormal returns. Positive risk-adjusted returns net of trading costs are documented solely during “up” markets for a portfolio long in prior winners only. The results on the international momentum effects indicate that the GA improves the momentum returns by 2 to 5% on an annual basis. In addition, the relation between momentum returns and exchange rate appreciation/depreciation is examined. The currency appreciation does not appear to influence significantly momentum profits. Further, the influence of the market state on momentum returns is not uniform across the countries considered. The implications of the above findings are discussed with a focus on the practical aspects of momentum investing, both in the U.S. and globally.

Genetic Algorithms and Investment Strategies: A Global Perspective

The profitability of momentum portfolios in the equity markets is derived from the continuation of stock returns over medium time horizons. The empirical evidence of momentum, however, is significantly different across markets around the world. The purpose of this dissertation is to: 1) help global investors determine the optimal selection and holding periods for momentum portfolios, 2) evaluate the profitability of the optimized momentum portfolios in different time periods and market states, 3) assess the investment strategy profits after considering transaction costs, and 4) interpret momentum returns within the framework of prior studies on investors’ behavior. Improving on the traditional practice of selecting arbitrary selection and holding periods, a genetic algorithm (GA) is employed. The GA performs a thorough and structured search to capture the return continuations and reversals patterns of momentum portfolios. Three portfolio formation methods are used: price momentum, earnings momentum, and earnings and price momentum and a non-linear optimization procedure (GA). The focus is on common equity of the U.S. and a select number of countries, including Australia, France, Germany, Japan, the Netherlands, Sweden, Switzerland and the United Kingdom. The findings suggest that the evolutionary algorithm increases the annualized profits of the U.S. momentum portfolios. However, the difference in mean returns is statistically significant only in certain cases. In addition, after considering transaction costs, both price and earnings and price momentum portfolios do not appear to generate abnormal returns. Positive risk-adjusted returns net of trading costs are documented solely during “up” markets for a portfolio long in prior winners only. The results on the international momentum effects indicate that the GA improves the momentum returns by 2 to 5% on an annual basis. In addition, the relation between momentum returns and exchange rate appreciation/depreciation is examined. The currency appreciation does not appear to influence significantly momentum profits. Further, the influence of the market state on momentum returns is not uniform across the countries considered. The implications of the above findings are discussed with a focus on the practical aspects of momentum investing, both in the U.S. and globally.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

The DCA:SOMe comparison: a comparative study between two biologically-inspired algorithms

The dendritic cell algorithm (DCA) is an immune-inspired algorithm, developed for the purpose of anomaly detection. The algorithm performs multi-sensor data fusion and correlation which results in a ‘context aware’ detection system. Previous applications of the DCA have included the detection of potentially malicious port scanning activity, where it has produced high rates of true positives and low rates of false positives. In this work we aim to compare the performance of the DCA and of a self-organizing map (SOM) when applied to the detection of SYN port scans, through experimental analysis. A SOM is an ideal candidate for comparison as it shares similarities with the DCA in terms of the data fusion method employed. It is shown that the results of the two systems are comparable, and both produce false positives for the same processes. This shows that the DCA can produce anomaly detection results to the same standard as an established technique.