This paper presents an innovative new approach to investment portfolio design, which applies a discrete, state-based methodology to defining market states and making asset allocation decisions with respect to both current and future state membership. State membership is based on attributes taken from traditional finance and portfolio theory namely expected growth, and covariance. The transitional dynamics of the derived states are modeled as a Markovian process. Asset weighting and portfolio allocation decisions are made through an optimization-based approach coupled with heuristics that account for the probability of state membership and the quality of the state in terms of information provided.

Market participants often invoke the concept of discrete state when discussing financial markets. Bull market, bear market, depression, and recession are all terms that map to discrete market states. Mental models of how markets behave in each state and transition between states are then applied to decision-making. Implicit to that approach is the assumption that states are persistent and recurrent over time. This article seeks to formalize notions of discrete market states by proposing a parsimonious and innovative approach to segmenting periods of time into discrete states. The technique is demonstrated and evaluated in a series of case studies.

We measure the incidence of latency arbitrage for cross-listed stocks around the time of an exogenous shock that made the markets faster. Our sample is from NASDAQ Nordic and consists of Nordic blue chip firms listed and traded in multiple markets. We document a sharp decline in the incidence of cross-market arbitrage opportunities across the Nordic markets for cross-listed stocks from 2009 to 2010 and later. Over the five year sample period 77% of the observed cross-market arbitrage opportunities occurred in 2009 and 13% in 2010 and the remaining 10% spread over the last three years. The inside spread declines by, on average, 14.5 basis points or 53% from 2009 to 2013. Our results point to significant improvements in market efficiency and market quality as a result of the switch to a faster trading system.

Financial markets are often fragmented, introducing the possibility that quotes in identical securities may become crossed or locked. There are a number of theoretical explanations for the existence of crossed and locked quotes, including competition, simultaneous actions, inattentiveness, fee structure and market access. In this paper, we perform a simulation experiment designed to examine the effect of simple order routing procedures on the properties of a fragmented market consisting of a single security trading in two independent limit order books. The quotes in the two markets are connected solely by the routing decision of the market participants. We report on the health of the consolidated market as measured by the duration of crossed and locked states, as well as the spread and the volatility of transaction prices in the consolidated market. We aim to quantify exactly how the prevalence of order routing among a population of market participants affects properties of the consolidated market. Our model contributes to the zero-intelligence literature by treating order routing as an experimental variable. Additionally, we introduce a parsimonious heuristic for limit order routing, allowing us to study the effects of both market order routing and limit order routing. Our model refines intuition for the sometimes subtle relationships between the prevalence of order routing and various market measures. Our model also provides a benchmark for more complex agent-based models.

Electronic markets and automated trading have resulted in a drastic increase in the quantity and complexity of regulatory data. Reconstructing the limit order book and analyzing order flow is an emerging challenge for financial regulators. New order types, intra-market behavior, and other exchange functionality further complicate the task of understanding market behavior at multiple levels. Data visualizations have proven to be a fundamental tool for building intuition and enabling exploratory data analysis in many fields. In this paper, we propose the incorporation of visualizations in the workflow of multiple financial regulatory roles, including market surveillance, enforcement and supporting academic research.

Determining the value of intelligence can be a difficult problem. One way to value intelligence is to judge a document’s worth by its location within a structure of a given corpus of documents. Citation networks and Google’s PageRank algorithm are examples of valuing information based on its location within a structure. Dynamic network analysis (DNA) has been used to allow a multilayered approach to social network analysis by including multi-nodal networks and creating inferences across networks with common nodes. We introduce the application of the DNA layered approach to information networks in an attempt to determine the value of intelligence.

An agent-based model is a computer simulation driven by the individual decisions of programmed agents. Such models provide a promising alternative to traditional economic modeling in that they can fully capture the diversity of agents and the institutional detail of the underlying an economic system. In this paper, we provide a brief methodological review of the agent-based approach to modeling financial markets. We review the research strategy, which is organized into a discussion of formulation, implementation, verification and validation. We conclude the paper with a review of the domain focusing on modeling market participants and market institutions.

Agent-based modeling is alternative framework for providing explanations of the behavior of financial markets. In this paper, we consider a simple agent-based model designed to understand the effects of smart order routing in a multi-market setting. The goal is to understand how the prevalence of smart order routing results in different levels of market integration. We find that only a small percentage of smart order routing results in a remarkable level of market integration.

In this paper we introduce a simple model of multi-market trading. An identical security trades on two independent trading platforms. Prices and quotes are connected only by the strategic behavior of traders. The experimental design varies the degree to which traders monitor and act on information from both markets. We report on the degree of integration between the two markets as measured by the availability of arbitrage opportunities and the percentage of volume that trade throughs better quotes. Finally, we discuss the limits of integration with respect to our modeling assumptions.

The authors propose that valuation of information metrics developed near the end of the intelligence cycle are appropriate supplemental metrics for national security intelligence. Existing information and decision theoretic frameworks are often either inapplicable in the context of national security intelligence or they capture affects from inputs aside from just the information or intelligence. Applied information theory looks at the syntactic transmission of information rather than assigning it a quantitative value. Information economics determines the market value of information, which is also inapplicable in a national security intelligence context. Decision analysis can use the value of information to show the expected value of perfect information EVPI and the expected value of imperfect information EVII and although this method can be used with utility theory and not just monetary objectives, it has been shown that decision makers within the intelligence community IC have difficulty agreeing upon how to value objectives within analysis. Additionally, it is difficult to determine how decision makers use intelligence in the decision-making process, which makes existing decision theoretic methods problematic, and might include inputs from variables besides just the intelligence.

Limit order book simulations based on “zero-intelligence” or “entropy-maximizing” agents address two difficult issues in financial economics. First, the models address the significance of trading mechanisms by explicitly accounting for the logic of those mechanisms. Second, they avoid the difficulty of modeling human decision-making by generating orders stochastically. This paper reports on a computational experiment in which a strategic agent trading on endogenous market signals is embedded in an otherwise stochastic order book simulation. Under certain parameterizations of the model the agent is profitable despite the fact that the agent only employs market orders.

Regulators and policy makers, facing a complicated, fast-paced and quickly evolving marketplace, require new tools and decision aides to inform policy. Agent-based models, which are capable of capturing the organization of exchanges, intricacies of market mechanisms, and the heterogeneity of market participants, offer a powerful method for understanding the financial marketplace. To this end, we have worked to develop a flexible and adaptable agent-based model of financial markets that can be extended and applied to interesting policy questions. This paper presents the implementation of this model. In addition, it provides a small case study that demonstrates the possible uses of the model. The source code of the simulation has also been released and is available for use.

Electronic markets and automated trading have resulted in a drastic increase in the quantity and complexity of regulatory data. Regulatory analysis now includes detailed analysis of all messaging and communications related to electronic limit order books. New order types, intra-market behavior and other exchange functionality further complicate analysis. Data visualizations have proven to be a fundamental tool for building intuition and enabling exploratory data analysis in many fields. In this paper, we propose the incorporation of visualizations in the workflow of multiple financial regulatory roles, including market surveillance, enforcement, and academic research.

The technological advancement of financial markets has allowed for trade to move to being nearly entirely electronic, with the majority of trades placed by automated participants. This has resulted in drastic increases in the quantity and complexity of regulatory data. The processing and analyzing of these markets and participants have emerged as a serious challenge for financial regulators. New order types, intra-market behavior and other exchange functionality further complicate the task of understanding market behavior and events. Data visualizations have proven to be a fundamental tool for building intuition and enabling exploratory data analysis in many fields. In this paper, we propose the incorporation of visualizations in the workflow of multiple financial regulatory roles, including market surveillance, enforcement, and academic research.

We propose a zero-intelligence agent-based model of the E-Mini S&P 500 futures market, which allows for a close examination of the market microstructure. Several classes of agents are characterized by their order speed and order placement within the limit order book. These agents' orders populate the simulated market in a way consistent with real world participation rates. By modeling separate trading classes the simulation is able to capture interactions between classes, which are essential to recreating market phenomenon. The simulated market is validated against empirically observed characteristics of price returns and volatility. We therefore conclude that our agent based simulation model can accurately capture the key characteristics of the nearest months E-Mini S&P 500 futures market. Additionally, to illustrate the applicability of the simulation, experiments were run, which confirm the leading hypothesis for the cause of the May 6 th 2010 Flash Crash.

Electronic markets have emerged as popular venues for the trading of a wide variety of financial assets, and computer based algorithmic trading has also asserted itself as a dominant force in financial markets across the world. Identifying and understanding the impact of algorithmic trading on financial markets has become a critical issue for market operators and regulators. We propose to characterize traders' behavior in terms of the reward functions most likely to have given rise to the observed trading actions. Our approach is to model trading decisions as a Markov Decision Process (MDP), and use observations of an optimal decision policy to find the reward function. This is known as Inverse Reinforcement Learning (IRL), and a variety of approaches for this problem are known. Our IRL-based approach to characterizing trader behavior strikes a balance between two desirable features in that it captures key empirical properties of order book dynamics and yet remains computationally tractable. Using an IRL algorithm based on linear programming, we are able to achieve more than 90% classification accuracy in distinguishing High Frequency Trading from other trading strategies in experiments on a simulated E-Mini S&P 500 futures market. The results of these empirical tests suggest that High Frequency Trading strategies can be accurately identified and profiled based on observations of individual trading actions.

An agent-based model (ABM) has a structure, which includes a set of agents, a topology and an environment. A simplified conception of a financial market includes a set of market participants, a trading mechanism, and a set of securities. In a typical ABM of a financial market, the market participants are agents, the market mechanism is the topology and the exogenous flow of information into the market is the environment. A zero-intelligence ABM model of the E-Mini Futures Market is presented. Several classes of agents are characterized by their speed and placement of orders within the limit order book. The proposed minimum quote life rule is implemented in the simulation. The minimum quote life rule prevents new orders from being cancelled or modified before a given time limit. Through experimentation, trade-off curves are generated. Thereby, illustrating the usefulness of this ABM and its ability to inform ongoing financial policy debates.