Artificial Stock Research Articles

Intelligent agent-assisted adaptive order simulation system in the artificial stock market

Agent-based computational economics (ACE) has received increased attention and importance over recent years. Some researchers have attempted to develop an agent-based model of the stock market to investigate the behavior of investors and provide decision support for innovation of trading mechanisms. However, challenges remain regarding the design and implementation of such a model, due to the complexity of investors, financial information, policies, and so on. This paper will describe a novel architecture to model the stock market by utilizing stock agent, finance agent and investor agent. Each type of investor agent has a different investment strategy and learning method. A prototype system for supporting stock market simulation and evolution is also presented to demonstrate the practicality and feasibility of the proposed intelligent agent-based artificial stock market system architecture.

Comparison of photosynthetic eco-functions of water hyacinth and their environmental factors in different areas

Eichhornia crassipes Solms,commonly known as water hyacinth,is a bundler aquatic plant.It is widely used in sewage purification due to its well developed root system,strong reproductive ability and ultra-strong absorbency.Introduced into China as feed,it is recently moderately consumed as cultivation substrate of edible fungus and methane fermentation materials.In fact,it is now an importantly modern,low-carbon eco-agricultural resource.An experiment was therefore conducted to determine the physiological and ecological characteristics of different types of water hyacinth in different ecological environments.The experiment was carried out at the Jiangsu Academy of Agricultural Sciences experimental sites in Xueyan of Taihu Lake,Nanjing and Dianchi Lake in 2009.Different plant indices such as plant height,root length and dry weight were measured.Also photosynthetic parameters of leaves at different sits were measured using LI-6400 portable photosynthetic system.The related environmental factors such as light intensity,air temperature and relative humid were recorded as well.Different water hyacinth phenotypes were noted in different areas.Short shoot with long root water hyacinths were noted in Dianchi Lake(with shoot/root height ratio of 0.4±0.1).Then medium-long shoot with short root water hyacinths were observed in Nanjing(with shoot/root height ratio of 7.1±0.3).Also long shoot with medium-long root water hyacinths existed in Taihu Lake(with shoot/root height ratio of 2.0±0.2).Compared with those in Nanjing and Dianchi Lake,Pn(25.9～35.3 μmol·m 2·s 1) of water hyacinth at Taihu Lake was the highest for different leaf positions.The correlation coefficients between Pn and relative humidity in Nanjing,Pn and stomatal conductance(Gs) in Dianchi Lake,and relative humidity and transpiration rate(Tr) in Taihu Lake were 0.831**,0.769* and 0.818*(n=6),respectively.Correlation analysis showed that after light intensity,relative humidity was the next most important ecological driving factor of Pn.Difference in phenotype of water hyacinth in different areas had affected maximum photosynthetic potentials of water hyacinth.The strongest plant growth of water hyacinth in Taihu Lake was related with high photosynthetic capacity(Pmax=36.29±1.21 μmol·m 2·s 1) and light saturation point(LSP=2 350.0±69.0 μmol·m 2·s 1).Plant height and light compensation point(LCP),as well as shoot length and LSP were all positively correlated with correlation coefficients of 0.998* and 0.997*(n=10),respectively.The findings of the study were critical for high yield artificial stocking of water hyacinth.It was recommended that future breeding should focus on extensive adaptability of E.crassipes to light and temperature conditions.

Liquidity cost of market orders in the Taiwan Stock Market: A study based on an order-driven agent-based artificial stock market

We developed an order-driven agent-based artificial stock market to analyze the liquidity costs of market orders in the Taiwan Stock Market (TWSE). The agent-based stock market was based on the DFGIS model proposed by Daniels, Farmer, Gillemot, Iori and Smith (Daniels et al., 2003). We also improved the DFGIS model by using two average order size parameters. When tested on 10 stocks and securities in the market, the model-simulated liquidity costs were higher than those of the TWSE data. We identified some possible factors that have contributed to this result: 1) the overestimated effective market order size, which can be improved by using two average order size parameters; 2) the random market order arrival time designed in the DFGIS model; 3) the zero-intelligence of the artificial agents in our model; and 4) the price of the effective market order. We continued improving the model so that it could be used to study liquidity costs and to devise liquidation strategies for stocks and securities traded in the Taiwan Stock Market.

Emergence of opinion leaders based on agent model and its impact on stock prices

AbstractThe development of information technology has made it possible to obtain large amounts of information easily. Thus it appears likely that the impact on a society of word‐of‐mouth information communication and the like has been growing. In this paper, we propose a model of the emergence of opinion leaders based on word of mouth in an artificial stock market. The process of emergence of opinion leaders and the impact of opinion leaders on stock prices are verified by simulation. © 2011 Wiley Periodicals, Inc. Electr Eng Jpn, 177(2): 32–40, 2011; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.21163

Order aggressiveness, pre-trade transparency, and long memory in an order-driven market

Recent empirical research has documented that the state of the limit order book influences stock investors' strategies. Investors place more aggressive orders when the same side of the order book is thicker, and less aggressive orders when it is thinner. We conjecture and demonstrate that this behavior is related to long memories of trading volume, volatility, and order signs in stock markets. We investigate our conjecture in two types of artificial stock markets: a transparent market, in which agents observe all limit orders on both sides of the book and order volumes at those prices before they trade; and a less transparent market, in which agents observe only the best five bid and ask quotes with the depth available at these limit prices. The first market structure resembles certain actual stock exchanges in the level of pre-trade transparency, such as the Australian Stock Exchange, NYSE OpenBook, and the London Stock Exchange, whereas the second market structure is consistent with stock exchanges such as Euronext Paris, the Toronto Stock Exchange, the Tokyo Stock Exchange, and Hong Kong Exchanges and Clearing. We demonstrate that our long memory results are robust with different levels of pre-trade transparency, implying that the strategy constructed by the state of the order book is key for explaining long memories in many actual stock exchanges.

Building the model of artificial stock market based on JASA

This paper introduces the major function, system framework, running mechanism and core modules of JASA, an open source auction simulator software. Then it builds a new multi-agent artificial stock market modeling platform, named JASA+ by extending, improving JASA, and adding stock market normal quotas, price limits, stock traders, bid-ask strategies and graphic reports. It studies the effects of price limits on stock market via JASA+ platform. The experimental results demonstrate that with in some extent the price limit policy could improve the market efficiency and return, and reduce the bid-ask spread. JASA+ can simulate true stock market preferably, being different from SFI-ASM, a traditional research tool. JASA+ gives researchers a new thought and method in finance markets.

Dynamic trade execution: a grammatical evolution approach

Trade execution is concerned with the actual mechanics of buying or selling the desired amount of a financial instrument. Investors wishing to execute large orders face a tradeoff between market impact and opportunity cost. Trade execution strategies are designed to balance out these costs, thereby minimising total trading cost. Despite the importance of optimising the trade execution process, this is difficult to do in practice due to the dynamic nature of markets and due to our imperfect understanding of them. In this paper, we adopt a novel approach, combining an evolutionary methodology whereby we evolve high-quality trade execution strategies, with an agent-based artificial stock market, wherein the evolved strategies are tested. The evolved strategies are found to outperform a series of benchmark strategies and several avenues are suggested for future work.

Information-based multi-assets artificial stock market with heterogeneous agents

In this paper, an artificial stock market characterized by heterogeneous and informed agents is presented. The heterogeneous agents are seen as nodes of sparsely connected graphs. The agents trade risky assets and are characterized by sentiments, amount of cash and stocks owned. Agents share information and sentiments by means of interactions determined by graphs. A central market maker (clearing house mechanism) determines the price processes for each stock at the intersection of the demand and supply curves. In this framework, the statistical properties of the univariate and multivariate process of prices and returns are studied. Importantly, concerning univariate price processes, the proposed model is able to reproduce unit root, volatility cluster and fat tails of returns. The multivariate price process exhibits both static and dynamic stylized facts, in particular the presence of static factors and common trends. Static factors are studied making reference to the cross-correlation between returns of different stocks, whereas the common trends are investigated considering the variance–covariance matrix of prices. The proposed approach allows to endogenously reproduce the multivariate stylized facts.

Modeling investor sentiment and overconfidence in an agent-based stock market

Agent-based stock markets as bottom-up models of financial markets allow us to study the link between individual investor behavior and aggregate market phenomena, and as such are a useful tool for investigating the implications of behavioral finance and investor psychology. In this paper we want to disentangle between the effects of investor sentiment and investor overconfidence. While investor optimism or pessimism influences the expectations of future returns, overconfidence is related to the precision of those expectations and is modeled as miscalibration. In an artificial stock market based on the LLS model, we find that more optimistic investors create more pronounced booms and crashes in the market, when compared to the unbiased efficient market believers of the original model. In the case of extreme optimism, the optimistic investors end up dominating the market, while in the case of extreme pessimism, the market reduces to the benchmark model of rational informed investors. The overconfidence of investors is found to exacerbate the effects of investor sentiment.

Examining the effectiveness of price limits in an artificial stock market

This paper proposes an agent-based framework to examine the effectiveness of price limits in an artificial stock market. The market is composed of many boundedly rational and heterogeneous traders whose learning behavior is represented by a genetic programming algorithm. We calibrate the model to replicate several stylized facts observed in real financial markets. Based on this environment, the impacts of price limits are analyzed from the perspectives of volatility, price distortion, volume, and welfare. We find that the imposition of price limits possesses both positive and negative effects. However, compared with the market without price limits, appropriate price limits help to reduce volatility and price distortion, and increase the liquidity and welfare.

Heterogeneous information-based artificial stock market

In this paper, an information-based artificial stock market is considered. The market is populated by heterogeneous agents that are seen as nodes of a sparsely connected graph. Agents trade a risky asset in exchange for cash. Besides the amount of cash and assets owned, each agent is characterized by a sentiment. Moreover, agents share their sentiments by means of interactions that are identified by the graph. Interactions are unidirectional and are supplied with heterogeneous weights. The agent's trading decision is based on sentiment and, consequently, the stock price process depends on the propagation of information among the interacting agents, on budget constraints and on market feedback. A central market maker (clearing house mechanism) determines the price process at the intersection of the demand and supply curves. Both closed- and open-market conditions are considered. The results point out the validity of the proposed model of information exchange among agents and are helpful for understanding the role of information in real markets. Under closed market conditions, the interaction among agents' sentiments yields a price process that reproduces the main stylized facts of real markets, e.g. the fat tails of the returns distributions and the clustering of volatility. Within open-market conditions, i.e. with an external cash inflow that results in asset price inflation, also the unitary root stylized fact is reproduced by the artificial stock market. Finally, the effects of model parameters on the properties of the artificial stock market are also addressed.

A semi-formal specification for a generic model of artificial stock markets

Abstract Artificial stock markets are models design to capture essential properties of real stock markets in order to reproduce, analy ze or understand market dynamics with computational experiments. Since there is a large variety of real stock markets and trading strategies, a large number of different artificial sock markets have been proposed. The researchers need constantly to test new structures of markets and new strategies of investment. In this paper we use Gaia methodology to provide a semi-formal specification of a generic model for artificial stock markets. The model is flexible in the sense that it can be used to develop several market structures and trading strategies, it can also adapted to support additional aspects.

Market Efficiencies and Market Risks

In recent years numerous papers constructed or simulated financial markets at an agent level, aiming to explain the non-stationarity of price processes. All such papers agree that the heterogeneity of agents and of pricing models creates a dynamics in terms of pricing models used that explains not only the non-stationarity of price processes, but also stylised facts such as bubbles and fat tails. However, all these results issue from very specific parametric set-ups, and even if multiple approaches confirm it, there is no proof of the aforementioned results outside of such specifications. By modeling agents as black boxes that receive information that they transform into an output information, information according to which they then act upon the financial market, we show that the diversity of agents is directly associated to the resulting quality of the information efficiency of the market: homogenous agents lead to good information propagation but poor information aggregation by the price, while heterogenous agents lead to good information aggregation but poor information propagation. This difference in quality of efficiency explains, outside of any parametric model, the dynamics of the number of different pricing models used within artificial stock markets.

Assessment of Genetic Structure of Sea Trout (Salmo trutta truttaL.) Populations in the Nemunas River Tributaries Based on Mitochondrial DNA Variation

Adult sea trout individuals caught during their spawning migration in the Nemunas, Jūra, Vilnia and Žeimena rivers were analysed. The level of genetic variation was assessed in the samples by means of the mitochondrial DNA ND1 segment RFLP analysis. Five composite haplotypes were observed in the sea trout populations of the Nemunas basin with significant levels of interpopulation diversity allowing determination of separate management units. The genetic structure of the Vilnia sea trout population preliminary demonstrated the influence of the artificial stocking of farmed sea trout into this river. The total genetic variation in the sea trout populations from the Nemunas basin was compared to the existing data from other populations within the Baltic Sea drainage. According to the results of mtDNA analysis, populations of sea trout in Lithuanian rivers might be derived from eastern glacial refugia.

BUILDING AN ARTIFICIAL STOCK MARKET POPULATED BY REINFORCEMENT‐LEARNING AGENTS

In this paper we propose an artificial stock market model based on interaction of heterogeneous agents whose forward-looking behaviour is driven by the reinforcement-learning algorithm combined with some evolutionary selection mechanism. We use the model for the analysis of market self-regulation abilities, market efficiency and determinants of emergent properties of the financial market. Distinctive and novel features of the model include strong emphasis on the economic content of individual decision-making, application of the Q-learning algorithm for driving individual behaviour, and rich market setup. Along with that a parallel version of the model is presented, which is mainly based on research of current changes in the market, as well as on search of newly emerged consistent patterns, and which has been repeatedly used for optimal decisions’ search experiments in various capital markets.

An examination of genetic diversity and effective population size in Atlantic salmon populations

Effective population size (Ne) is an important parameter in the conservation of genetic diversity. Comparative studies of empirical data that gauge the relative accuracy of Ne methods are limited, and a better understanding of the limitations and potential of Ne estimators is needed. This paper investigates genetic diversity and Ne in four populations of wild anadromous Atlantic salmon (Salmo salar L.) in Europe, from the Rivers Oir and Scorff (France) and Spey and Shin (Scotland). We aimed to understand present diversity and historical processes influencing current population structure. Our results showed high genetic diversity for all populations studied, despite their wide range of current effective sizes. To improve understanding of high genetic diversity observed in the populations with low effective size, we developed a model predicting present diversity as a function of past demographic history. This suggested that high genetic diversity could be explained by a bottleneck occurring within recent centuries rather than by gene flow. Previous studies have demonstrated the efficiency of coalescence models to estimate Ne. Using nine subsets from 37 microsatellite DNA markers from the four salmon populations, we compared three coalescence estimators based on single and dual samples. Comparing Ne estimates confirmed the efficiency of increasing the number and variability of microsatellite markers. This efficiency was more accentuated for the smaller populations. Analysis with low numbers of neutral markers revealed uneven distributions of allelic frequencies and overestimated short-term Ne. In addition, we found evidence of artificial stock enhancement using native and non-native origin. We propose estimates of Ne for the four populations, and their applications for salmon conservation and management are discussed.

Temporal structure and gain-loss asymmetry for real and artificial stock indices

Previous research has shown that for stock indices, the most likely time until a return of a particular size has been observed is longer for gains than for losses. We demonstrate that this so-called gain-loss asymmetry vanishes if the temporal dependence structure is destroyed by scrambling the time series. We also show that an artificial index constructed by a simple average of a number of individual stocks display gain-loss asymmetry-this allows us to explicitly analyze the dependence between the index constituents. We consider mutual information and correlation-based measures and show that the stock returns indeed have a higher degree of dependence in times of market downturns than upturns.

Multi-fractarity Analysis of Artificial Stock Prices Generated by Multi-agent using Genetic Programming for Learning and its Applications

Multi-fractarity Analysis of Artificial Stock Prices Generated by Multi-agent using Genetic Programming for Learning and its Applications

The Interplay Between Two Stock Markets and a Related Foreign Exchange Market: A Simulation Approach

There is still much that is unknown about the interactions among financial markets, and about the relationships between stock prices and exchange rates. This topic gains attention during financial crises, and many papers try to find empirical regularities emerging from financial data, or to study contagion processes. In this paper we present a study on the interplay between two stock markets and one foreign exchange market extending the framework provided by the Genoa Artificial Stock Market. There are four different trading strategies, and the agents are divided into two groups: those who trade in the stock markets and those who trade in the FOREX. We studied three market conditions: the FOREX dynamics, the behavior of the two stock markets together with the FOREX, and finally we conducted a what-if analysis for testing the effects of a inflationary monetary shock of one currency affecting all of the three markets.

Modeling and Simulation of an Artificial Stock Option Market

Since their introduction in 1973, options have become an important and very popular financial instrument. However, despite much research performed on the subject, the effects of option trading on the underlying asset market are still debated. Both empirical and theoretical studies have failed to point out how price volatility and volumes of the underlying asset are affected. In this paper we present the first study on the effects of an option market related to an underlying stock market, using an artificial financial market based on heterogeneous agents. We modeled a realistic European option using two market models. The microstructure of the first model is kept as simple as possible, being composed only of random traders. The second model is more complex and realistic, involving the presence of various kinds of trading strategies (random, fundamentalist and chartist). We show that the introduction of options, in the proposed models, tends to decrease the volatility of the underlying stock price. Moreover, the traders' wealth can be strongly affected by the use of option hedging.