Showing papers on "Electronic trading published in 2017"
01 Aug 2017
TL;DR: This work proposes a deep learning methodology, based on recurrent neural networks, that can be used for predicting future price movements from large-scale high-frequency time-series data on Limit Order Books.
Abstract: Forecasting financial time-series has long been among the most challenging problems in financial market analysis. In order to recognize the correct circumstances to enter or exit the markets investors usually employ statistical models (or even simple qualitative methods). However, the inherently noisy and stochastic nature of markets severely limits the forecasting accuracy of the used models. The introduction of electronic trading and the availability of large amounts of data allow for developing novel machine learning techniques that address some of the difficulties faced by the aforementioned methods. In this work we propose a deep learning methodology, based on recurrent neural networks, that can be used for predicting future price movements from large-scale high-frequency time-series data on Limit Order Books. The proposed method is evaluated using a large-scale dataset of limit order book events.
118 citations
TL;DR: In this paper, the authors study intraday market intermediation in an electronic market before and during a period of large and temporary selling pressure, and find that the trading pattern of the most active non-designated high frequency traders (classified as High Frequency Traders) did not change when prices fell during the Flash Crash.
Abstract: We study intraday market intermediation in an electronic market before and during a period of large and temporary selling pressure. On May 6, 2010, U.S. financial markets experienced a systemic intraday event, known as the Flash Crash, when a large automated sell program was rapidly executed in the E-mini S&P 500 stock index futures market. Using audit trail transaction-level data for the E-mini on May 6 and the previous three days, we find that the trading pattern of the most active non-designated intraday intermediaries (classified as High Frequency Traders) did not change when prices fell during the Flash Crash.
90 citations
TL;DR: The article argues that political-economic struggles are integral to the existence of some of the ‘pockets’ of predictable structure in the otherwise random movements of prices, to the availability of the data that allow algorithms to identify these pockets, and to the capacity of algorithms to use these predictions to trade profitably.
Abstract: This article contains the first detailed historical study of one of the new high-frequency trading (HFT) firms that have transformed many of the world's financial markets. The study, of Automated Trading Desk (ATD), one of the earliest and most important such firms, focuses on how ATD's algorithms predicted share price changes. The article argues that political-economic struggles are integral to the existence of some of the 'pockets' of predictable structure in the otherwise random movements of prices, to the availability of the data that allow algorithms to identify these pockets, and to the capacity of algorithms to use these predictions to trade profitably. The article also examines the role of HFT algorithms such as ATD's in the epochal, fiercely contested shift in US share trading from 'fixed-role' markets towards 'all-to-all' markets.
64 citations
TL;DR: In this article, the authors assess the microstructure of the U.S. Treasury securities market following its migration to electronic trading and show that both trades and limit orders affect price dynamics, suggesting that traders also choose limit orders to exploit their information.
59 citations
TL;DR: In this paper, the authors investigate how lit and dark market fragmentation affects liquidity and find that neither dark trading nor fragmentation between lit order books is found to harm liquidity, or at worst does not affect them.
45 citations
01 Jun 2017
TL;DR: A novel rule discovery mechanism using a GA approach is proposed for solving optimization problems of rough set analysis when discovering technical trading rules for the futures market and the results show that the proposed model significantly outperforms the benchmark model in terms of the average return and as a risk-adjusted measure.
Abstract: Display Omitted This study proposes an intelligent hybrid trading system for discovering technicaltrading rules.This study deals with the optimization problem of data discretization and reducts.Rough set analysis is adopted to represent trading rules.A genetic algorithm is used to discover optimal and sub-optimal trading rules.To evaluate the proposed system, a sliding window method is applied. Discovering intelligent technical trading rules from nonlinear and complex stock market data, and then developing decision support trading systems, is an important challenge. The objective of this study is to develop an intelligent hybrid trading system for discovering technical trading rules using rough set analysis and a genetic algorithm (GA). In order to obtain better trading decisions, a novel rule discovery mechanism using a GA approach is proposed for solving optimization problems (i.e., data discretization and reducts) of rough set analysis when discovering technical trading rules for the futures market. Experiments are designed to test the proposed model against comparable approaches (i.e., random, correlation, and GA approaches). In addition, these comprehensive experiments cover most of the current trading system topics, including the use of a sliding window method (with or without validation dataset), the number of trading rules, and the size of training period. To evaluate an intelligent hybrid trading system, experiments were carried out on the historical data of the Korea Composite Stock Price Index 200 (KOSPI 200) futures market. In particular, trading performance is analyzed according to the number of sets of decision rules and the size of the training period for discovering trading rules for the testing period. The results show that the proposed model significantly outperforms the benchmark model in terms of the average return and as a risk-adjusted measure.
41 citations
TL;DR: The actor-based analysis confirms the prevalent view that interbank credit is mainly determined by lasting business relationships and less so by competition for the best price (interest rate), and shows that topological features exert a certain influence on the network formation process.
26 citations
TL;DR: The contours of a HFT world are outlined, including market manipulation, hacking, index construction and violence, and the issue of time as embodied in algorithmic trading is raised.
Abstract: This article examines the financial security issues raised by the rapid development of high-frequency trading (HFT). HFT involves automated algorithmic trading of financial instruments where the objective is to reduce the time scale between the initiation and execution of trades to microseconds (or even nanoseconds) so as to reap competitive advantage. After outlining the contours of a HFT world, the presentation goes on to discuss some of its important consequences and implications. Several matters are discussed in this context: market manipulation, hacking, index construction and violence. Of particular significance for the notion of financial security is the issue of time as embodied in algorithmic trading. In turn this raises concerns over the regulation and management of this new field of financial innovation and trading activity.
24 citations
TL;DR: This article showed that the U.S. Supreme Court's decision in the case of Morrison v. National Australia Bank in June 2010 was associated with a statistically significant increase in the price deviation between the underlying home-market shares and the cross-listed shares.
Abstract: We show that the U.S. Supreme Court’s ruling in the case of Morrison v. National Australia Bank in June of 2010 was associated with a statistically significant 37 basis point increase on the day in the price deviation between the U.S. cross-listed shares trading in U.S. markets and the underlying home-market shares. The Court unexpectedly ruled that the main fraud-related provisions of U.S. securities laws can apply only to transactions in foreign securities that take place in the U.S. Across our sample of almost 1,000 foreign firms from 42 different countries cross-listed on the major U.S. exchanges as well as those trading on over-the-counter (OTC) markets, the price deviations between the cross-listed and underlying home-market shares widened more dramatically for those companies with a lower presence in the U.S. as measured by the fraction of global trading that takes place in U.S. markets. The market’s revaluation of the cross-listed shares around the decision is consistent with the idea that investors care about the extent to which U.S. securities laws apply, an important driver of the bonding role that U.S. markets play.
23 citations
TL;DR: This paper used a proprietary dataset to test the implications of several asymmetric information models on how short-lived private information affects trading strategies and liquidity provision, and provided the first empirical evidence supporting theoretical predictions that early-informed traders "sell the news" after "buying the rumor".
Abstract: We use a proprietary dataset to test the implications of several asymmetric information models on how short-lived private information affects trading strategies and liquidity provision. Our identification rests on information acquisition before analyst recommendations are publicly announced. We provide the first empirical evidence supporting theoretical predictions that early-informed traders “sell the news” after “buying the rumor.” Further, we find distinct profit-taking patterns across different classes of institutions. Uninformed institutions, but not individuals, emerge as de-facto liquidity providers to better-informed institutions. Placebo tests confirm that these trading patterns are unique to situations in which some investors have a short-lived informational advantage.
22 citations
TL;DR: In this paper, the authors test two complementary theories of optimal trading strategies by analyzing transaction patterns of corporate insiders: information-based theories predict that investors trade faster if they compete with others for exploiting the same information.
Abstract: We test two complementary theories of optimal trading strategies by analyzing transaction patterns of corporate insiders: Information-based theories predict that investors trade faster if they compete with others for exploiting the same information. Liquidity-based theories pre-dict the opposite. Our analysis supports the predictions of liquidity-based models: insiders take longer to complete trades when they face competition from other insiders and they trade more slowly in less liquid markets. Insiders also adapt to fluctuations in market liquidity. We use abnormal returns to identify informed trading and show that for this subset of trades, the predictions of information-based models are supported.
TL;DR: In this paper, the authors examined the informational content of an electronic order book and found that order flow imbalances have a moderate capacity to predict short-term price changes, however, both LOB slope and immediacy costs help to forecast quote improvements and volatility in the next 30min.
TL;DR: In this paper, a review of the literature on high frequency trading with empirical data from interviews with financial traders, computer experts and regulators is presented, where concepts of regulatory adaptation, technology asymmetry, and market ambiguity are developed to illustrate the dark art of high-frequency trading.
Abstract: Computerization has transformed financial markets with high frequency trading displacing human activity with proprietary algorithms to lower latency, reduce intermediary costs, enhance liquidity and increase transaction speed. Following the “Flash Crash” of 2010 which saw the Dow Jones Industrial Average plunge 1000 points within minutes, high frequency trading has come under the radar of multi-jurisdictional regulators. Combining a review of the extant literature on high frequency trading with empirical data from interviews with financial traders, computer experts and regulators, we develop concepts of regulatory adaptation, technology asymmetry and market ambiguity to illustrate the ‘dark art’ of high frequency trading. Findings show high frequency trading is a multi-faceted, complex and secretive practice. It is implicated in market events, but correlation does not imply causation, as isolating causal mechanisms from interconnected automated financial trading is highly challenging for regulators who seek to monitor algorithmic trading across multiple jurisdictions. This article provides information systems researchers with a set of conceptual tools for analysing high frequency trading.
30 May 2017
TL;DR: Overall, the prototype implements the basic software structure of this decentralized market framework, illustrates the feasibility of decentralized market mechanisms, and highlights potential use cases as well as limitations.
Abstract: As an infrastructure for economic systems, blockchain technology challenges the role of traditional intermediaries and enables the creation of novel market designs and value chains We utilize this potential and design a decentralized market framework that allows users to trade complex financial assets, such as stocks, in an intermediary-free setup Overall, our prototype implements the basic software structure of this market framework, illustrates the feasibility of decentralized market mechanisms, and highlights potential use cases as well as limitations
TL;DR: In this article, the authors argue that there are two main types of technical trading rules, namely rules based on trend-following and mean reversion, and show that mean-reversion based rules perform increasingly better as sampling frequencies increase and that conversely the performance of trend following rules deteriorate at higher-frequencies.
TL;DR: In this paper, the authors examined the impact of CDS trading and the lifting of short sales restrictions on the profitability of reported insider trades within US financial firms and found evidence that executive directors possess significant insider knowledge about their firm's risk prior to the initiation of cDS trading.
TL;DR: In this paper, the authors adopt the lens of long-run growth to understand how improvements in financial technology shape information choices, trading strategies and market efficiency, as measured by price informativeness and market liquidity.
Abstract: In most sectors, technological progress boosts efficiency But financial technology and the associated data-intensive trading strategies have been blamed for market inefficiency A key cause for concern is that better technology might induce traders to extract other's information from order flow data mining, rather than produce information themselves Defenders of these new trading strategies argue that they provide liquidity by identifying uninformed orders and taking the other side of their trades We adopt the lens of long-run growth to understand how improvements in financial technology shape information choices, trading strategies and market efficiency, as measured by price informativeness and market liquidity We find that unbiased technological change can explain a market-wide shift in data collection and trading strategies But our findings also cast doubt on common wisdom First, although extracting information from order flow does crowd out production of fundamental information, this does not compromise price informativeness Second, although taking the opposite side of uninformed trades is typically called "providing liquidity," the rise of such trading strategies does not necessarily improve liquidity in the market as a whole
14 Aug 2017
TL;DR: The experiments showed that trading behaviors in the financial market could be explained by the physical trends of a quantitative and technical analysis of the market profile theory, and it was proven that the financial trading market follows the existence of a certain trading logic.
Abstract: Day trading has become an important topic of discussion in the last decades, especially with regard to computer program trading or the increasing trend of high-frequency transactions. However, due to the high level of complexity regarding the forecasting of day trading trends, the use of traditional financial analysis or technical indicators for the forecasting of short-term market trends is often ineffective. The main reason is that in addition to the technical analysis of market physical trends, financial market trading behaviors are also often affected by psychological factors such as greed and fear, which are emotions displayed by investors during the transaction process. For this reason, this study will use the neural network to integrate into the financial engineering technology analysis of the physical momentum behavior and market profile theory to quantify controlled learning. The goal is to be able to provide an empirical explanation of the discoveries related to trading behaviors by using trading strategies. Our experiments showed that trading behaviors in the financial market could be explained by the physical trends of a quantitative and technical analysis of the market profile theory. It has also been proven that the financial trading market follows the existence of a certain trading logic.
TL;DR: In this article, a multi-slice trading network of manipulated stocks and non-manipulated stocks was constructed to characterize the daily trading behavior and the cross-day participation of each trader.
Abstract: Manipulation is an important issue for both developed and emerging stock markets. Many efforts have been made to detect manipulation in stock market. However, it is still an open problem to identify the fraudulent traders, especially when they collude with each other. In this paper, we focus on the problem of identifying anomalous traders using the transaction data of 8 manipulated stocks and 42 non-manipulated stocks during a one-year period. For each stock, we construct a multi-slice trading network to characterize the daily trading behavior and the cross-day participation of each trader. Comparing the multi-slice trading network of manipulated stocks and non-manipulated stocks with their randomized version, we find that manipulated stocks exhibit high number of trader pairs that trade with each other in multiple days and high deviation from randomized network at correlation between trading frequency and trading activity. These findings are effective at distinguishing manipulated stocks from non-manipulated ones and at identifying anomalous traders.
Posted Content•
TL;DR: In this paper, the role of technology driven information categories in influencing trading decisions in electronic markets was examined and the results showed that a variation of information categories can influence trading performance and can be used to explain anomalies as well as to manage trading performance.
Abstract: Electronic trading markets have evolved rapidly with continued adoption of new technologies and growing information acquisition and processing capabilities. Traditional perspectives on trading performance adopted a monolithic view of information. Past research and practitioner heuristics posit that adopting new technologies and incorporating more information should increase price efficiency and trading performance uniformity. However, along with technological change, in-formation dynamics have evolved significantly resulting in immense growth in data volumes, and increased complexity of information categories. The present research explores behavioral trading performance under varying information category conditions and argues that unfettered technological developments and information consumption will not necessarily lead to consistent improvement in uniformity of trading performance. In this study, we employ an artificial stock market based economic experiment to examine the role of technology driven information categories in influencing trading decisions in electronic markets. Financial electronic markets are used as an information-rich mature markets representation to analyze information category driven trading performance. The results show that a variation of information categories can influence trading performance. The findings provide a basis to better understand behavioral phenomena in electronic markets and can be used to explain anomalies as well as to manage trading performance in electronic markets.
TL;DR: The exercise sought to address problems associated with continuous markets that have been described in recent literature, and the design of the refinement is described, and its consequences are discussed.
Abstract: This letter describes an exercise in market mechanism refinement that was recently undertaken on a major electronic trading venue: Thomson Reuters Matching. The exercise sought to address problems associated with continuous markets that have been described in recent literature. To this end, the design of the refinement is described, and its consequences are discussed.
TL;DR: In this paper, the authors model a two-tiered market structure in which an investor can trade an asset on a trading platform with a set of dealers who in turn have access to an interdealer market.
Abstract: We model a two-tiered market structure in which an investor can trade an asset on a trading platform with a set of dealers who in turn have access to an interdealer market. The investor's order is informative about the asset's payoff and dealers who were contacted by the investor use this information in the interdealer market. Increasing the number of contacted dealers lowers markups through competition but increases the dealers' costs of providing the asset through information leakage. We then compare a centralized market in which investors can trade among themselves in a central limit order book to a market in which investors have to use the electronic platform to trade the asset. With imperfect competition among dealers, investor welfare is higher in the centralized market if private values are strongly dispersed or if the mass of investors is large.
01 Jan 2017
TL;DR: What temporal fairness is and is not, things that can make it elusive are identified, and a mechanism for improving it is described that was recently retrofitted to a major FX trading venue: Thomson Reuters Matching.
Abstract: Fairness, in general, is a topic that has received much attention in research on distributed systems. In their application as electronic trading venues, however, temporal fairness remains a topic that is poorly understood. This is concerning because operators of these venues generally have obligations to ensure their fairness. Consequently, this paper (1) describes what temporal fairness is and is not, (2) identifies things that can make it elusive, and (3) describes a mechanism for improving it that was recently retrofitted to a major FX trading venue: Thomson Reuters Matching.
TL;DR: In this article, the authors investigated the impact of electronic trading on the informational efficiency of the TSX and found that the introduction of automated trading led to an increase in linearity dependence in TSX daily returns.
TL;DR: In this article, the effect of high-frequency trading on market efficiency in the European fragmented market landscape was studied. And the authors found that HFT increases market efficiency by leveling midpoints between Euronext Paris and Bats Chi-X Europe.
Abstract: Securities trading underwent a major transformation within the last decade. This transformation was mainly driven by the regulatory induced fragmentation and by the increase of high-frequency trading (HFT). On the basis of the electronic market hypothesis, which poses that coordination costs decline when markets become automated, and the efficient market hypothesis in its semi-strong form, we study the effect of HFT on market efficiency in the European fragmented market landscape. In doing so, we further incorporate the realm of financialization, which criticizes the increase in transaction speed. By conducting a long-term analysis of CAC 40 securities, we find that HFT increases market efficiency by leveling midpoints between Euronext Paris and Bats Chi-X Europe. On the basis of a cross-country event study, we analyze the effect of the German HFT Act. We observe that the midpoint dispersion of blue chip securities between the two leading venues Deutsche Boerse and Bats Chi-X Europe increased. We conclude that HFT increases market efficiency in the European market landscape by transmitting information between distant markets.
01 Dec 2017
TL;DR: In this paper, a metric that captures the minimum extent to which an ETV's performance must be inhibited by buffering so as to rectify the temporal unfairness it would otherwise exhibit is proposed.
Abstract: Electronic trading venues (ETVs) must simultaneously exhibit high degrees of both fairness and performance, yet in diverse contexts it is recognized trade-offs often exists between these two things. Introduced in this paper is a metric that captures the minimum extent to which an ETV's performance must be inhibited by buffering so as to rectify the temporal unfairness it would otherwise exhibit. In light of 'tail latency', and so as to minimize the value it takes, a refinement of the metric is further described using a finding from queue theory pertaining to skips and slips. The metric and its associated buffering mechanism have recently been put into actual use on a major ETV: Thomson Reuters Matching.
TL;DR: This paper investigated the impact of exogenous trading glitch at a high-frequency market-making firm on standard measures of stock liquidity (effective and realized spreads) as well as on institutional trading costs (Implementation Shortfall and VWAP slippage) obtained from a proprietary data set.
Abstract: We investigate the impact of an exogenous trading glitch at a high-frequency market-making firm on standard measures of stock liquidity (effective and realized spreads) as well as on institutional trading costs (Implementation Shortfall and VWAP slippage) obtained from a proprietary data set. We find that stocks in which the firm accumulated large positions as a result of the trading glitch become substantially more illiquid on the day of the glitch. Effective spreads revert very quickly suggesting that market liquidity is resilient. Instead, institutional trading costs remain significantly higher for more than one week. We further document that all stocks for which the firm was a designated market maker become more illiquid, even if they were not heavily traded during the glitch, in the two days prior to being reassigned to another market maker. These findings are broadly consistent with 'slow-moving capital' theories and suggest that high-frequency trading 'flash crashes' may be associated with significant costs that are difficult to detect using standard liquidity measures.
TL;DR: In this paper, a trading strategy that relies on private information in an electronic spot foreign exchange market is investigated, and the authors find that large currency orders are likely to be placed by informed traders during increased price volatility episodes.
Patent•
15 Mar 2017
TL;DR: In this paper, a trading platform network for rarities is provided, which includes at least one raritymine, an online merchandising convergence, and input from a robo-rarity trading data stream.
Abstract: A trading platform network for rarities is provided. The network includes at least one raritymine, an online merchandising convergence, and input from a robo-rarity trading data stream. According to this aspect, rarityminers are enabled to view virtual three-dimensional depictions of rarity assets contained in the at least one raritymine and buy and sell raritybits. A rarities trading exchange toolkit which includes the trading platform network and a rarity system is also provided.
TL;DR: There is no single “language” and an approach to design the logistics networks, with a proper level of detail that takes into account the strategic features and industry specificity of the certain company, according to the modern methods and approaches used.
Abstract: Abstract This article considers the modern methods and approaches to design the company’s distribution network. The authors point out the relevance of this problem for the modern trading and manufacturing companies, give examples of the strategic goal setting of the company in the logistics network reorganization, and the benchmarks of possible economic effects of its conduction. The work reviews the scientific articles of contemporary American, European and Russian authors devoted to the approaches, concerning the implementation of projects for designing a distribution network, methods and models for its optimization. The article concludes that there is no single “language” and an approach to design the logistics networks, with a proper level of detail that takes into account the strategic features and industry specificity of the certain company. The authors propose an algorithm for designing a rational distribution network.