Antoaneta Serguieva

Profiling high-frequency equity price movements in directional changes

Market prices are traditionally sampled in fixed time intervals to form time series. Directional change (DC) is an alternative approach to record price movements. Instead of sampling at fixed intervals, DC is data driven: price changes dictate when a price is recorded. DC provides us with a complementary way to extract information from data. It allows us to observe features that may not be recognized in time series. The argument is that time series and DC-based analysis complement each other. With data sampled at irregular time intervals in DC, however, some of the time series indicators cannot be used in DC-based analysis. For example, returns must be time adjusted and volatility must be amended accordingly. A major objective of this paper is to introduce indicators for profiling markets under DC. We analyse empirical high-frequency data on major equities traded on the UK stock market, and through DC profiling extract information complementary to features observed through time series profiling.

FN-TOPSIS: Fuzzy Networks for Ranking Traded Equities

Fuzzy systems consisting of networked rule bases, called fuzzy networks, capture various types of imprecision inherent in financial data and in the decision-making processes on them. This paper introduces a novel extension of the technique for ordering of preference by similarity to ideal solution (TOPSIS) method and uses fuzzy networks to solve multicriteria decision-making problems where both benefit and cost criteria are presented as subsystems. Thus, the decision maker evaluates the performance of each alternative for portfolio optimization and further observes the performance for both benefit and cost criteria. This approach improves significantly the transparency of the TOPSIS methods, while ensuring high effectiveness in comparison with established approaches. The proposed method is further tested to solve the problem of selection/ranking of traded equity covering developed and emergent financial markets. The ranking produced by the method is validated using Spearman rho rank correlation. Based on the case study, the proposed method outperforms the existing TOPSIS approaches in terms of ranking performance.

Financial contagion simulation through modelling behavioural characteristics of market participants and capturing cross-market linkages

Over the past two decades, financial market crises with similar features have occurred in different regions of the world. Unstable cross-market linkages during financial crises are referred to as financial contagion. We simulate the transmission of financial crises in the context of a model of market participants adopting various strategies; this allows testing for financial contagion under alternative scenarios. Using a comprehensive approach, we develop an agent-based multinational model and identify factors contributing to contagion. Although contagion has been investigated in the financial literature, it has not yet been studied extensively through computational intelligence techniques. The first steps in that direction are taken in [1],[2],[3],[4]. We extend these studies and introduce GARCH model and Clayton copula to better capture markets interdependence and to improve the evolutionary optimization technique. Our model further comprises four rather than three types of traders: technical, game, herd, and noise traders, respectively. The different types of traders use different strategies to make now three rather than two kinds of decisions: “buy”, “sell”, or ”hold”. Our simulations shed light on parameter values and characteristics which can be exploited in further research to detect contagion at an earlier stage, hence recognizing financial crises with the potential to destabilize cross-market linkages.

Guest Editorial Special Issue on Fuzzy Techniques in Financial Modeling and Simulation

The papers in this special section focus on the use of fuzzy techniques and logic for use in financial modeling and simulation. Computational intelligence has attracted a significant and increasing interest from the financial engineering community, and an emerging interest from analytical economics groups. The bar has been raised with the revision of regulations, and the required compliance and risk management. The new rules should be implemented through new processes and supported by developing new computational tools. Computational systems, capturing sentiments, preferences, behavior, and beliefs, are becoming indispensable in financial applications and desirable in economic analysis. They address problems in the classification of credit worthiness and fraud detection, contribute to the analysis and pricing of financial instruments, and effectively support portfolio optimization and investment analysis. They are instrumental in the design of market mechanisms and contagion mechanisms, and are contributing to the simulation of micro- and macro-economic processes. The armory of fuzzy techniques is capable of addressing challenges encountered in financial engineering and analytical economics. Fuzzy logic can effectively describe and incorporate expertsź intuition, market participantsź preferences, and economic agentsź behavior, thus reaching beyond the capabilities of probabilistic models. The objective of this special issue is to bring together the most recent advances in the design and application of fuzzy approaches to real problems in financial engineering and analytical economics.

Multichannel Contagion vs Stabilisation in Multiple Interconnected Financial Markets

The theory of multilayer networks is in its early stages, and its development provides vital methods for understanding complex systems. Multilayer networks, in their multiplex form, have been introduced within the last three years to analysing the structure of financial systems, and existing studies have modelled and evaluated interdependencies of different type among financial institutions. These studies, however, have considered the structure as a non-interconnected multiplex - an ensemble of single layer networks comprising the same nodes - rather than as an interconnected multiplex network. No mechanism of multichannel contagion has been modelled and empirically evaluated, and no multichannel stabilisation strategies for pre-emptive contagion containment have been designed. This paper formulates an interconnected multiplex structure, and a contagion mechanism among financial institutions due to bilateral exposures arising from institutions activity within different interconnected markets that compose the overall financial market. We introduce structural measures of absolute systemic risk and resilience, and relative systemic-risk indexes. Based on the contagion mechanism and systemic-risk quantification, this study designs minimum-cost stabilisation strategies that act simultaneously on different markets and their interconnections, in order to effectively contain potential contagion progressing through the overall structure. The stabilisation strategies subtly affect the emergence process of structure to adaptively build in structural resilience and achieve pre-emptive stabilisation at a minimum cost for each institution and at no cost for the system as a whole. We empirically evaluate the new approach using large granular databases, maintained by the Prudential Regulatory Authority of the Bank of England. The capabilities of multichannel stabilisation are confirmed empirically.

Developing sustainable trading strategies using directional changes with high frequency data

Market prices are traditionally recorded in fixed time intervals. Directional Change is an alternative approach to summarize price movements in financial markets that is consistent with across all time scales. Unlike time series, directional change summarizes the big data in finance by focusing on the intrinsic time of the data. This captures deeper intrinsic data qualities and thus trading strategies based on directional change are more sustainable and less disruptive. In this paper, we propose four trading strategies using the concept of directional change and explore the combination with technical analysis. The trading strategies are tested using EUR/USD and GBP/USD high frequency FX market data. Empirical results show good performance of our trading strategies based on thresholds, and that combining with technical analysis brings further improvement.

Special Issue of Quantitative Finance on ‘Financial Data Analytics’

Data are everywhere. The data universe is far richer and more far-reaching than it was a decade, five or even three years ago. Data are collected routinely on platforms and via media undreamed of a short while ago. And so much of these data are relevant to finance. Who would have thought, in the pre-Twitter world, that discussion threads could be connected to market risk appetite? Or those algorithms could begin to detect how much information asymmetry exists in a market? The focus of this Special Issue is to draw together connected papers which use the astonishing breadth of data available today, together with advances in computational techniques, to deliver insights into sectors of the financial world which could previously only be speculated upon. We begin with papers which have done novel work in the area of textual analysis. Rönnqvist and Sarlin study the Reuters online news archive, which contains approximately three million articles, to understand the degree to which banks are connected and interdependent—this could prove to be a useful indicator of risk in an era where the phrase ‘too big to fail’ has come into common parlance. Conceivably too much connectivity could serve as an indicator of needed structural changes. Yang, Mo and Liu have focused on the Twitter financial community and whether it can predict stock market movement. This elegant paper first constructs the financial community within Twitter using network techniques, and then shows that critical ‘nodes’ within this community are significantly correlated with major financial market indices. Yaros and Imieliński use text analysis of equity analyst coverage and news articles to show that market sentiment expressed in these media gives a good indication of the future similarity and correlations of different equity markets, a technique which could have significant utility for the construction of investment portfolios. The next paper is more relevant to those who study the activity, motivation and methodology of the trading community. Algorithmic trading, where deals in the market are executed according to predefined rules and without human intervention, has become commonplace in the market. However, the impact of this algorithmic execution on market dynamics is uncertain, and thus a rich data universe has been gathered on trading patterns from different institutions and individuals. Yang, Qiao, Beling, Scherer and Kirilenko utilize these data to spot trading patterns unique to individuals or particular algorithms, enabling them to identify which traders or execution platforms are active at different times. This additionally allows them to identify to some extent the drivers behind traders’ actions under different market conditions. After this, we enter the world of machine learning. In recent years, there has been a degree of discussion about whether hedge fund returns are really due to the skill and experience of their portfolio managers, or whether they could be created more cheaply from simple underlying assets. Payne and Tresl perform a comprehensive study on over 4500 stocks to show that genetic algorithms can be used to create replicating portfolios of simple underlying assets like stocks, bonds and mutual funds, which show good out-of-sample correlation with the hedge fund returns. Next, Wilinski, Cui, Brabazon and Hamill analyse individual trades on the London Stock Exchange. They include an examination of time-of-day effects which is new and significantly shows that price impact is the highest at the start of the trading day and the lowest towards the end, important information for those with large flows to execute. Finally, Panayi, Peters and Kosmidis offer a large-scale study of liquidity and liquidity resilience, using high frequency data to show that resilience is only partly explained by market factors, but at extreme levels is dominated by individual asset factors. We hope this Special Issue provides valuable insights into the rapidly growing area of data analytics in finance and contributes to the advances of this field. We thank the contributing authors; the referees for their valuable input and the Editors-in-Chief for their support.

Direct Participants’ Behavior Through the Lens of Transactional Analysis: The Case of SPEI®

This paper presents a methodology to study the flow of funds in large value payment systems (LVPSs). The presented algorithm separates the flow of payments in two categories: (1) external funds, i.e. funds transferred from other financial market infrastructures (FMIs) or provided by the central bank and (2) the reuse of incoming payments. Our method further studies the flow of intraday liquidity under the framework of its provision within the Mexican FMIs. The aim is to evaluate the impact of the intraday liquidity provision, and understand how liquidity is transmitted to participants in the Mexican LVPS SPEI®;.

IEEE CIFEr 2014 - Leading Forum on Computational Finance and Economics Research in Academia and Industry [Conference Reports]

The IEEE Conference on Computational Intelligence for Financial Engineering and Economics (CIFEr) is now established as a leading research forum at the interface between academia and industry. This year the biennial event was held on 27-28 March in London, and praised by the participants and presenters for the excellent organization, beautiful and functional venue, and high quality of keynote talks, panel discussions, and technical sessions. The authors provide an overview of events of note that took place at the conference.

Financial Contagion: A Propagation Simulation Mechanism

A simulation mechanism is designed for crisis propagation accommodating contagion. A new co-evolutionary market model is described, where some of the technical traders change their behaviour during crisis and their decisions become largely influenced by market sentiment rather than based on fundamental factors and underlying strategies. Analyzing agents’ behaviour, it is observed that the herd mentality intensifies during crisis. This paper focuses on the transformation of market interdependence into contagion, and on contagion effects. A multi-national platform is build first, to allow different type of players to implement their trading strategies while considering information from both domestic and foreign markets. Traders’ strategies and the performance of the simulated domestic market is trained using historic prices of domestic and foreign markets, while optimizing artificial markets’ parameters through immune particle swarm optimization techniques. Further elements are introduced contributing to the transformation of technical into herd traders. A GARCH-copula is applied next to calculate the tail dependence between the affected market and the origin of the crisis. That parameter is used in the fitness function for selecting the best solutions within the evolving population of possible model parameters, and therefore in the optimization criteria for contagion simulation. The results show that the proportion of herd traders increases in the net market order for optimum contagion simulations. While technical traders’ behaviour corresponds to propagating a crisis through interdependence, herd behaviour corresponds to propagating through contagion. If contagion could be avoided or transformed back to interdependence, with the timely response of national governments and international institutions, a crisis would be more manageable. Further research could introduce a recovery mechanism … into the model through the design of national and international intervention.