Cramer, S., Kampouridis, M. and Freitas, A. (2018). Decomposition Genetic Programming: An Extensive Evaluation on Rainfall Prediction in the Context of Weather Derivatives. Applied Soft Computing[Online]70:208-224. Available at: https://doi.org/10.1016/j.asoc.2018.05.016.
Regression problems provide some of the most challenging research opportunities in the area of machine learning,
where the predictions of some target variables are critical to a specific application. Rainfall is a prime example, as it
exhibits unique characteristics of high volatility and chaotic patterns that do not exist in other time series data. Moreover,
rainfall is essential for applications that surround financial securities, such as rainfall derivatives. This paper
extensively evaluates a novel algorithm called Decomposition Genetic Programming (DGP), which is an algorithm
that decomposes the problem of rainfall into subproblems. Decomposition allows the GP to focus on each subproblem,
before combining back into the full problem. The GP does this by having a separate regression equation for
each subproblem, based on the level of rainfall. As we turn our attention to subproblems, this reduces the difficulty
when dealing with data sets with high volatility and extreme rainfall values, since these values can be focused on
independently. We extensively evaluate our algorithm on 42 cities from Europe and the USA, and compare its performance
to the current state-of-the-art (Markov chain extended with rainfall prediction), and six other popular machine
learning algorithms (Genetic Programming without decomposition, Support Vector Regression, Radial Basis Neural
Networks, M5 Rules, M5 Model trees, and k-Nearest Neighbours). Results show that the DGP is able to consistently
and significantly outperform all other algorithms. Lastly, another contribution of this work is to discuss the effect that
DGP has had on the coverage of the rainfall predictions and whether it shows robust performance across different
Kampouridis, M. and Otero, F. (2017). Heuristic procedures for improving the predictability of a genetic programming financial forecasting algorithm. Soft Computing[Online]21:295-310. Available at: http://dx.doi.org/10.1007/s00500-015-1614-8.
Financial forecasting is an important area in computational finance. Evolutionary Dynamic Data Investment Evaluator (EDDIE) is an established genetic programming (GP) financial forecasting algorithm, which has successfully been applied to a number of international financial datasets. The purpose of this paper is to further improve the algorithm's predictive performance, by incorporating heuristics in the search. We propose the use of two heuristics: a sequential covering strategy to iteratively build a solution in combination with the GP search and the use of an entropy-based dynamic discretisation procedure of numeric values. To examine the effectiveness of the proposed improvements, we test the new EDDIE version (EDDIE 9) across 20 datasets and compare its predictive performance against three previous EDDIE algorithms. In addition, we also compare our new algorithm's performance against C4.5 and RIPPER, two state-of-the-art classification algorithms. Results show that the introduction of heuristics is very successful, allowing the algorithm to outperform all previous EDDIE versions and the well-known C4.5 and RIPPER algorithms. Results also show that the algorithm is able to return significantly high rates of return across the majority of the datasets.
Cramer, S. et al. (2017). An extensive evaluation of seven machine learning methods for rainfall prediction in weather derivatives. Expert Systems with Applications[Online]85:169-181. Available at: https://doi.org/10.1016/j.eswa.2017.05.029.
Regression problems provide some of the most challenging research opportunities in the area of machine learning, and more broadly intelligent systems, where the predictions of some target variables are critical to a specific application. Rainfall is a prime example, as it exhibits unique characteristics of high volatility and chaotic patterns that do not exist in other time series data. This work's main impact is to show the benefit machine learning algorithms, and more broadly intelligent systems have over the current state-of-the-art techniques for rainfall prediction within rainfall derivatives. We apply and compare the predictive performance of the current state-of-the-art (Markov chain extended with rainfall prediction) and six other popular machine learning algorithms, namely: Genetic Programming, Support Vector Regression, Radial Basis Neural Networks, M5 Rules, M5 Model trees, and k-Nearest Neighbours. To assist in the extensive evaluation, we run tests using the rainfall time series across data sets for 42 cities, with very diverse climatic features. This thorough examination shows that the machine learning methods are able to outperform the current state-of-the-art. Another contribution of this work is to detect correlations between different climates and predictive accuracy. Thus, these results show the positive effect that machine learning-based intelligent systems have for predicting rainfall based on predictive accuracy and with minimal correlations existing across climates.
Alexandridis, A., Kampouridis, M. and Cramer, S. (2017). A Comparison between Wavelet Networks and Genetic Programming in the Context of Temperature Derivatives. International Journal of Forecasting[Online]33:21-47. Available at: http://www.sciencedirect.com/science/article/pii/S0169207016300711.
The purpose of this study is to develop a model that accurately describes the dynamics of the daily average temperature in the context of weather derivatives pricing. More precisely we compare two state of the art machine learning algorithms, namely wavelet networks and genetic programming, against the classic linear approaches widely used in the pricing of temperature derivatives in the financial weather market and against various machine learning benchmark models such as neural networks, radial basis functions and support vector regression. The accuracy of the valuation process depends on the accuracy of the temperature forecasts. Our proposed models are evaluated and compared in-sample and out-of-sample in various locations where weather derivatives are traded. Furthermore, we expand our analysis by examining the stability of the forecasting models relative to the forecasting horizon. Our findings suggest that the proposed nonlinear methods significantly outperform the alternative linear models, with wavelet networks ranking first, and can be used for accurate weather derivative pricing in the weather market.
Vastardis, N., Kampouridis, M. and Yang, K. (2016). A user behaviour-driven smart-home gateway for energy management. Journal of Ambient Intelligence and Smart Environments[Online]8:583-602. Available at: http://dx.doi.org/10.3233/AIS-160403.
Current smart-home and automation systems have reduced generality and modularity, thus confining users in terms of functionality. This paper proposes a novel system architecture and describes the implementation of a user-centric smart-home gateway that is able to support home-automation, energy usage management and reduction, as well as smart-grid operations. This is enabled through a middleware service that exposes a control API, allowing the manipulation of the home network devices and information, irrespectively of the involved technologies. Additionally, the system places the users as the prime owners of their data, which in turn is expected to make them much more willing to install and cooperate with the system. The gateway is supported by a centralised user-centric machine-learning component that is able to extract behavioural patterns of the users and feed them back to the gateway. The results presented in this paper demonstrate the efficient operation of the gateway and examine two well-know machine learning algorithms for identifying patterns in the user's energy consumption behaviour. This feature could be utilised to improve its performance and even identify energy saving opportunities.
Kim, Y. et al. (2016). Discrete Dynamics in Evolutionary Computation and Its Applications. Discrete Dynamics in Nature and Society[Online]2016:1-2. Available at: https://doi.org/10.1155/2016/6043597.
Kampouridis, M., Otero, F. and Kampouridis, M. (2016). Evolving Trading Strategies Using Directional Changes. Expert Systems with Applications[Online]73:145-160. Available at: http://dx.doi.org/10.1016/j.eswa.2016.12.032.
The majority of forecasting methods use a physical time scale for studying price fluctuations of financial markets, making the flow of physical time discontinuous. Therefore, using a physical time scale may expose companies to risks, due to ignorance of some significant activities. In this paper, an alternative and original approach is explored to capture important activities in the market. The main idea is to use an event-based time scale based on a new way of summarising data, called Directional Changes. Combined with a genetic algorithm, the proposed approach aims to find a trading strategy that maximises profitability in foreign exchange markets. In order to evaluate its efficiency and robustness, we run rigorous experiments on 255 datasets from six different currency pairs, consisting of intra-day data from the foreign exchange spot market. The results from these experiments indicate that our proposed approach is able to generate new and profitable trading strategies, significantly outperforming other traditional types of trading strategies, such as technical analysis and buy and hold.
Kampouridis, M., Alsheddy, A. and Tsang, E. (2013). On the investigation of hyper-heuristics on a financial forecasting problem. Annals of Mathematics and Artificial Intelligence[Online]68:225-246. Available at: http://dx.doi.org/10.1007/s10472-012-9283-0.
Financial forecasting is a really important area in computational finance, with numerous works in the literature. This importance can be reflected in the literature by the continuous development of new algorithms. Hyper-heuristics have been successfully used in the past for a number of search and optimization problems, and have shown very promising results. To the best of our knowledge, they have not been used for financial forecasting. In this paper we present pioneer work, where we use different hyper-heuristics frameworks to investigate whether we can improve the performance of a financial forecasting tool called EDDIE 8. EDDIE 8 allows the GP (Genetic Programming) to search in the search space of indicators for solutions, instead of using pre-specified ones; as a result, its search area has dramatically increased and sometimes solutions can be missed due to ineffective search. We apply 14 different low-level heuristics to EDDIE 8, to 30 different datasets, and examine their effect to the algorithm's performance. We then select the most prominent heuristics and combine them into three different hyper-heuristics frameworks. Results show that all three frameworks are competitive, and are able to show significantly improved results, especially in the case of best results. Lastly, analysis on the weights of the heuristics shows that there can be a constant swinging among some of the low-level heuristics, which denotes that the hyper-heuristics frameworks are able to 'know' the appropriate time to switch from one heuristic to the other, based on their effectiveness
Kampouridis, M., Chen, S. and Tsang, E. (2012). Market Fraction Hypothesis: A proposed test. International Review of Financial Analysis[Online]23:41-54. Available at: http://dx.doi.org/10.1016/j.irfa.2011.06.009.
This paper presents and formalizes the Market Fraction Hypothesis (MFH), and also tests it under empirical datasets. The MFH states that the fraction of the different types of trading strategies that exist in a financial market changes (swings) over time. However, while such swinging has been observed in several agent-based financial models, a common assumption of these models is that the trading strategy types are static and pre-specified. In addition, although the above swinging observation has been made in the past, it has never been formalized into a concrete hypothesis. In this paper, we formalize the MFH by presenting its main constituents. Formalizing the MFH is very important, since it has not happened before and because it allows us to formulate tests that examine the plausibility of this hypothesis. Testing the hypothesis is also important, because it can give us valuable information about the dynamics of the market''s microstructure. Our testing methodology follows a novel approach, where the trading strategies are neither static, nor pre-specified, as in the case in the traditional agent-based financial model literature. In order to do this, we use a new agent-based financial model which employs genetic programming as a rule-inference engine, and self-organizing maps as a clustering machine. We then run tests under 10 international markets and find that some parts of the hypothesis are not well-supported by the data. In fact, we find that while the swinging feature can be observed, it only happens among a few strategy types. Thus, even if many strategy types exist in a market, only a few of them can attract a high number of traders for long periods of time.
Kampouridis, M. and Tsang, E. (2012). Investment Opportunities Forecasting: Extending the Grammar of a GP-based Tool. International Journal of Computational Intelligence Systems[Online]5:530-541. Available at: http://dx.doi.org/10.1080/18756891.2012.696918.
In this paper we present a new version of a GP financial forecasting tool, called EDDIE 8. The novelty of this version is that it allows the GP to search in the space of indicators, instead of using pre-specified ones. We compare EDDIE 8 with its predecessor, EDDIE 7, and find that new and improved solutions can be found. Analysis also shows that, on average, EDDIE 8's best tree performs better than the one of EDDIE 7. The above allows us to characterize EDDIE 8 as a valuable forecasting tool.
Kampouridis, M., Chen, S. and Tsang, E. (2012). Microstructure Dynamics and Agent-Based Financial Markets: Can Dinosaurs Return?Advances in Complex Systems[Online]15:1250060. Available at: http://dx.doi.org/10.1142/S0219525912500609.
This paper formalizes observations made under agent-based artificial stock market models into a concrete hypothesis, which is called the Dinosaur Hypothesis. This hypothesis states that the behavior of financial markets constantly changes and that the trading strategies in a market need to continuously co-evolve with it in order to remain effective. After formalizing the hypothesis, we suggest a testing methodology and run tests under 10 international financial markets. Our tests are based on a framework that we recently developed, which used Genetic Programming as a rule inference engine, and Self-Organizing Maps as a clustering machine for the above rules. However, an important assumption of that study was that maps among different periods were directly comparable with each other. In order to allow this to happen, we had to keep the same clusters throughout the different time periods of our experiments. Nevertheless, this assumption could be considered as strict or even unrealistic. In this paper, we relax this assumption. This makes our model more realistic. In addition, this allows us to investigate in depth the dynamics of market behavior and test for the plausibility of the Dinosaur Hypothesis. The results show that indeed markets' behavior constantly changes. As a consequence, strategies need to continuously co-evolve with the market; if they do not, they become obsolete or dinosaurs.
Read More: http://www.worldscientific.com/doi/abs/10.1142/S0219525912500609
Kampouridis, M., Chen, S. and Tsang, E. (2011). The Market Fraction Hypothesis under different GP algorithms. in:Information Systems for Global Financial Markets: Emerging Developments and Effects,.IGI Global, pp. 37-54.
Kampouridis, M., Chen, S. and Tsang, E. (2011). Market Microstructure: A Self-Organizing Map Approach for Investigating Behavior Dynamics under an Evolutionary Environment. in:Natural Computing in Computational Finance,.Springer, pp. 181-197.
Adegboye, A., Kampouridis, M. and Johnson, C. (2018). Regression genetic programming for estimating trend end in foreign exchange market. in:IEEE Symposium Series on Computational Intelligence.IEEE. Available at: http://dx.doi.org/10.1109/SSCI.2017.8280833.
Most forecasting algorithms use a physical time scale for studying price movement in financial markets, making the flow of physical time discontinuous. The use of a physical time scale can make companies oblivious to significant activities in the market, which poses a risk. Directional changes is a different and newer approach, which uses an event-based time scale. This approach summarises data into alternating trends called upward directional change and downward directional change. Each of these trends are further dismembered into directional change (DC) event and overshoot (OS) event. We present a genetic programming (GP) algorithm that evolves equations that express linear and non-linear relationships between the length of DC and OS events in a given dataset. This allows us to have an expectation when a trend will reverse, which can lead to increased profitability. This novel trend reversal estimation approach is then used as part of a DC-based trading strategy. We aim to appraise whether the new knowledge can lead to greater excess return. We assess the efficiency of the modified trading strategy on 250 different datasets from five different currency pairs, consisting of intraday data from the foreign exchange (Forex) spot market. Results show that our algorithm is able to return profitable trading strategies and statistically outperform state-of-the-art financial trading strategies, such as technical analysis, buy and hold and other DC-based trading strategies.
Kampouridis, M., Adegboye, A. and Johnson, C. (2017). Evolving Directional Changes Trading Strategies with a New Event-based Indicator. in:SEAL 2017 : The 11th International Conference on Simulated Evolution and Learning.pp. 727-738. Available at: https://doi.org/10.1007/978-3-319-68759-9_59.
The majority of forecasting methods use a physical time scale for studying price fluctuations of financial markets, making the flow of physical time discontinuous. An alternative to this is event-based summaries. Directional changes (DC), which is a new event-based summary method, allows for new regularities in data to be discovered and exploited, as part of trading strategies. Under this paradigm, the timeline is divided in directional change events (upwards or downwards), and overshoot events, which follow exactly after a directional change has been identified. Previous work has shown that the duration of overshoot events is on average twice the duration of a DC event. However, this was empirically observed on the specific currency pairs DC was tested with, and only under the specific time periods the tests took place. Thus, this observation is not easily generalised. In this paper, we build on this regularity, by creating a new event-based indicator. We do this by calculating the average duration time of overshoot events on each training set of each individual dataset we experiment with. This allows us to have tailored duration values for each dataset. Such knowledge is important, because it allows us to more accurately anticipate trend reversal. In order to take advantage of this new indicator, we use a genetic algorithm to combine different DC trading strategies, which use our proposed indicator as part of their decision-making process. We experiment on 5 different foreign exchange currency pairs, for a total of 50 datasets. Our results show that the proposed algorithm is able to outperform its predecessor, as well as other well-known financial benchmarks, such as a technical analysis.
Cramer, S. et al. (2017). Pricing Rainfall Based Futures Using Genetic Programming. in:20th European Conference, EvoApplications: European Conference on the Applications of Evolutionary Computation.Springer, pp. 17-33. Available at: http://dx.doi.org/10.1007%2F978-3-319-55849-3_2.
Rainfall derivatives are in their infancy since starting trading on the Chicago Mercantile Exchange (CME) since 2011. Being a relatively new class of financial instruments there is no generally recognised pricing framework used within the literature. In this paper, we propose a novel framework for pricing contracts using Genetic Programming (GP). Our novel framework requires generating a risk-neutral density of our rainfall predictions generated by GP supported by Markov chain Monte Carlo and Esscher transform. Moreover, instead of having a single rainfall model for all contracts, we propose having a separate rainfall model for each contract. We compare our novel framework with and without our proposed contract-specific models for pricing against the pricing performance of the two most commonly used methods, namely Markov chain extended with rainfall prediction (MCRP), and burn analysis (BA) across contracts available on the CME. Our goal is twofold, (i) to show that by improving the predictive accuracy of the rainfall process, the accuracy of pricing also increases. (ii) contract-specific models can further improve the pricing accuracy. Results show that both of the above goals are met, as GP is capable of pricing rainfall futures contracts closer to the CME than MCRP and BA. This shows that our novel framework for using GP is successful, which is a significant step forward in pricing rainfall derivatives.
Cramer, S., Kampouridis, M. and Freitas, A. (2016). A Genetic Decomposition Algorithm for Predicting Rainfall within Financial Weather Derivatives. in:Genetic and Evolutionary Computation Conference (GECCO 2016).
Regression problems provide some of the most challenging research opportunities, where the predictions of such domains are critical to a specific application. Problem domains that exhibit large variability and are of chaotic nature are the most challenging to predict. Rainfall being a prime example, as it exhibits very unique characteristics that do not exist in other time series data. Moreover, rainfall is essential for applications that surround financial securities such as rainfall derivatives. This paper is interested in creating a new methodology for increasing the predictive accuracy of rainfall within the problem domain of rainfall derivatives. Currently, the process of predicting rainfall within rainfall derivatives is dominated by statistical models, namely Markov-chain extended with rainfall prediction (MCRP). In this paper, we propose a novel algorithm for decomposing rainfall, which is a hybrid Genetic Programming/Genetic Algorithm (GP/GA) algorithm. Hence, the overall problem becomes easier to solve. We compare the performance of our hybrid GP/GA, against MCRP, Radial Basis Function and GP without decomposition. We aim to show the effectiveness that a decomposition algorithm can have on the problem domain. Results show that in general decomposition has a very positive effect by statistically outperforming GP without decomposition and MCRP.
Cramer, S., Kampouridis, M. and Freitas, A. (2016). Feature Engineering for Improving Financial Derivatives-based Rainfall Prediction. in:IEEE World Congress on Evolutionary Computation.
Rainfall is one of the most challenging variables to predict, as it exhibits very unique characteristics that do not exist in other time series data. Moreover, rainfall is a major component and is essential for applications that surround water resource planning. In particular, this paper is interested in extending previous work carried out on the prediction of rainfall using Genetic Programming (GP) for rainfall derivatives. Currently in the rainfall derivatives literature, the process of predicting rainfall is dominated by statistical models, namely using a Markov-chain extended with rainfall prediction (MCRP). In this paper we further extend our new methodology by looking at the effect of feature engineering on the rainfall prediction process. Feature engineering will allow us to extract additional information from the data variables created. By incorporating feature engineering techniques we look to further tailor our GP to the problem domain and we compare the performance of the previous GP, which previously statistically outperformed MCRP, against our new GP using feature engineering on 21 different data sets of cities across Europe and report the results. The goal is to see whether GP can outperform its predecessor without extra features, which acts as a benchmark. Results indicate that in general GP using extra features significantly outperforms a GP without the use of extra features.
Cramer, S. et al. (2016). Predicting Rainfall in the Context of Rainfall Derivatives Using Genetic Programming. in:IEEE Computational Intelligence for Financial Engineering & Economics, Symposium Series on Computational Intelligence.IEEE, pp. 711-718. Available at: https://doi.org/10.1109/SSCI.2015.108.
Rainfall is one of the most challenging variables to predict, as it exhibits very unique characteristics that do not exist in other time series data. Moreover, rainfall is a major component and is essential for applications that surround water resource planning. In particular, this paper is interested in the prediction of rainfall for rainfall derivatives. Currently in the rainfall derivatives literature, the process of predicting rainfall is dominated by statistical models, namely using a Markov-chain extended with rainfall prediction (MCRP). In this paper we outline a new methodology to be carried out by predicting rainfall with Genetic Programming (GP). This is the first time in the literature that GP is used within the context of rainfall derivatives. We have created a new tailored GP to this problem domain and we compare the performance of the GP and MCRP on 21 different data sets of cities across Europe and report the results. The goal is to see whether GP can outperform MCRP, which acts as a benchmark. Results indicate that in general GP significantly outperforms MCRP, which is the dominant approach in the literature.
Gypteau, J., Otero, F. and Kampouridis, M. (2015). Generating Directional Change Based Trading Strategies with Genetic Programming. in:Mora, A. M. and Squillero, G. eds.EvoApplications, EvoStar 2015.Springer, pp. 1-12.
Brookhouse, J., Otero, F. and Kampouridis, M. (2014). Working with OpenCL to Speed Up a Genetic Programming Financial Forecasting Algorithm: Initial Results. in:16th International Conference on Genetic and Evolutionary Computation (GECCO 2014).pp. 1117-1124. Available at: http://dx.doi.org/10.1145/2598394.2605689.
The genetic programming tool EDDIE has been shown to be a successful financial forecasting tool, however it has suffered from an increase in execution time as new features have been added. Speed is an important aspect in financial problems, especially in the field of algorithmic trading, where a delay in taking a decision could cost millions. To offset this performance loss, EDDIE has been modified to take advantage of multi-core CPUs and dedicated GPUs. This has been achieved by modifying the candidate solution evaluation to use an OpenCL kernel, allowing the parallel evaluation of solutions. Our computational results have shown improvements in the running time of EDDIE when the evaluation was delegated to the OpenCL kernel running on a multi-core CPU, with speed ups up to 21 times faster than the original EDDIE algorithm. While most previous works in the literature reported significantly improvements in performance when running an OpenCL kernel on a GPU device, we did not observe this in our results. Further investigation revealed that memory copying overheads and branching code in the kernel are potentially causes of the (under-)performance of the OpenCL kernel when running on the GPU device.
Shao, M. et al. (2014). Guided Fast Local Search for Speeding Up a Financial Forecasting Algorithm. in:IEEE Computational Intelligence for Financial Engineering & Economics (CIFEr).
Aluko, B. et al. (2014). Combining different meta-heuristics to improve the predictability of a financial forecasting algorithm. in:IEEE Computational Intelligence for Financial Engineering & Economics (CIFEr).
Otero, F. and Kampouridis, M. (2014). A Comparative Study on the Use of Classification Algorithms in Financial Forecasting. in:EvoApplications 2014.Springer-Verlag Berlin, pp. 276-287. Available at: http://dx.doi.org/10.1007/978-3-662-45523-4_23.
Financial forecasting is a vital area in computational finance, where several studies have taken place over the years. One way of viewing financial forecasting is as a classification problem, where the goal is to find a model that represents the predictive relationships between predictor attribute values and class attribute values. In this paper we present a comparative study between two bio-inspired classification algorithms, a genetic programming algorithm especially designed for financial forecasting, and an ant colony optimization one, which is designed for classification problems. In addition, we compare the above algorithms with two other state-of-the-art classification algorithms, namely C4.5 and RIPPER. Results show that the ant colony optimization classification algorithm is very successful, significantly outperforming all other algorithms in the given classification problems, which provides insights for improving the design of specific financial forecasting algorithms.
Kampouridis, M. and Otero, F. (2013). Using attribute construction to improve the predictability of a GP financial forecasting algorithm. in:Technologies and Applications of Artificial Intelligence (TAAI 2013).pp. 55-60. Available at: http://dx.doi.org/10.1109/TAAI.2013.24.
Financial forecasting is an important area in computational finance. EDDIE 8 is an established Genetic Programming financial forecasting algorithm, which has successfully been applied to a number of international datasets. The purpose of this paper is to further increase the algorithm's predictive performance, by improving its data space representation. In order to achieve this, we use attribute construction to create new (high-level) attributes from the original (low-level) attributes. To examine the effectiveness of the above method, we test the extended EDDIE's predictive performance across 25 datasets and compare it to the performance of two previous EDDIE algorithms. Results show that the introduction of attribute construction benefits the algorithm, allowing EDDIE to explore the use of new attributes to improve its predictive accuracy.
Smonou, D., Kampouridis, M. and Tsang, E. (2013). Metaheuristics Application on a Financial Forecasting Problem. in:IEEE Congress on Evolutionary Computation (IEEE CEC 2013).
Kampouridis, M. et al. (2012). Using a Genetic Algorithm as a Decision Support Tool for the Deployment of Fiber Optic Networks. in:Proceedings of the IEEE World Congress on Computational Intelligence.Brisbane, Australia.
Kampouridis, M. and Tsang, E. (2011). Using Hyperheuristics under a GP framework for Financial Forecasting. in:Proc. Fifth International Conference on Learning and Intelligent Optimization (LION5).Springer, Heidelberg, pp. 16-30.
Kampouridis, M., Chen, S. and Tsang, E. (2011). Market Microstructure: Can Dinosaurs Return? A Self-Organizing Map Approach under an Evolutionary Framework. in:EvoApplications, EvoStar 2011.pp. 91-100.
Chen, S., Kampouridis, M. and Tsang, E. (2011). Microstructure Dynamics and Agent-Based Financial Markets. in:Multi-Agent-Based Simulation XI, 11th International Workshop, Revised Papers, LNAI.Berlin Heidelberg: Springer-Verlag, pp. 121-135.
Kampouridis, M., Chen, S. and Tsang, E. (2011). Investigating the Effect of Different GP Algorithms on the Non-Stationary Behavior of Financial Markets. in:Computational Intelligence for Financial Engineering and Economics.IEEE Press.
Kampouridis, M., Chen, S. and Tsang, E. (2010). Testing the Dinosaur Hypothesis Under Different GP Algorithms. in:Proceedings of the UK Computational Intelligence Workshop (UKCI), IEEE Xplore.Essex, pp. 1-7.
Kampouridis, M. and Tsang, E. (2010). EDDIE for Investment Opportunities Forecasting: Extending the Search Space of the GP. in:Proceedings of the IEEE World Congress on Computational Intelligence.Barcelona, Spain, pp. 2019-2026.
Chen, S., Kampouridis, M. and Tsang, E. (2010). Microstructure Dynamics and Agent-Based Financial Markets. in:Proceedings of the 11th International Workshop on Multi-Agent-Based Simulation (MABS 2010).Toronto, Canada, pp. 117-128.