Universal features of price formation in financial markets: perspectives from deep learning

Using a large-scale Deep Learning approach applied to a high-frequency database containing billions of market quotes and transactions for US equities, we uncover nonparametric evidence for the existence of a universal and stationary relation between order flow history and the direction of price moves. The universal price formation model exhibits a remarkably stable out-of-sample accuracy across a wide range of stocks and time periods. Interestingly, these results also hold for stocks which are not part of the training sample, showing that the relations captured by the model are universal and not asset-specific.

The universal model—trained on data from all stocks—outperforms asset-specific models trained on time series of any given stock. This weighs in favor of pooling together financial data from various stocks, rather than designing asset- or sector-specific models, as is currently commonly done. Standard data normalizations based on volatility, price level or average spread, or partitioning the training data into sectors or categories such as large/small tick stocks, do not improve training results. On the other hand, inclusion of price and order flow history over many past observations improves forecast accuracy, indicating that there is path-dependence in price dynamics.     

Information provision in financial markets

We set up a rational expectations model in which investors trade a risky asset based on a private signal they receive about the quality of the asset, and a public signal that represents a noisy aggregation of the private signals of all investors. Our model allows us to examine what happens to market performance (market depth, price efficiency, volume of trade, and expected welfare) when regulators can induce improved information provision in one of two ways. Regulations can be designed that either provide investors with more accurate information by improving the quality of prior information, or that enhance the transparency of the market by improving the quality of the public signal. In our rational expectations equilibrium, improving the quality of the public signal can be interpreted as a way of providing information about the anticipations and trading motives of all market participants. We find that both alternatives improve market depth. However, in the limit, we show that improving the precision of prior information is a more efficient way to do so. More accurate prior information decreases asymmetric information problems and consequently reduces the informativeness of prices, while a more accurate public signal increases price informativeness. The volume of trade is independent of the quality of prior information and is increasing in the quality of the public signal. Finally, expected welfare can sometimes fall as prior information or the public signal become more precise.     

全球金融市场在动荡中发展

2007年12月,国际清算银行发布了季度报告,对次贷危机威胁下的全球金融市场进行回顾,报告显示,市场遭受持续的信用恐慌打击,主要工业经济体的国债收益率显著下降,衍生品市场创下最繁忙记录,国际银行业跨境债权增长由急变缓（截至2007年6月末）。     

Measuring large comovements in financial markets

A general, copula-based framework for measuring the dependence among financial time series is presented. Particular emphasis is placed on multivariate conditional Spearman's rho (MCS), a new measure of multivariate conditional dependence that describes the association between large or extreme negative returns—so-called tail dependence. We demonstrate that MCS has a number of advantages over conventional measures of tail dependence, both in theory and in practical applications. In the analysis of univariate financial series, data are filtered to remove temporal dependence as a matter of routine. We show that standard filtering procedures may strongly influence the conclusions drawn concerning tail dependence. We give empirical applications to two large data sets of high-frequency asset returns. Our results have immediate implications for portfolio risk management, derivative pricing and portfolio selection. In this context we address portfolio tail diversification and tail hedging. Amongst other aspects, it is shown that the proposed modeling framework improves the estimation of portfolio risk measures such as the value at risk.     

CRM in intermediated financial services markets

A division of a major UK insurance company manufactures insurance products for wholesale clients to retail into their banking and building society customer bases. This paper discusses the CRM challenges of leveraging insurance business from existing partnership relationships, including issues of confidentiality between client portfolios, the strategic use of data marts rather than data warehouses and the sharing of information. It describes the issues involved in implementing CRM, such as rolling out customer contact management and call centre systems. The study concludes with an appraisal of lessons learned, which include a better understanding of who the customers are and which of them are profitable, together with the characteristics that contribute to them becoming profitable or unprofitable.     

进一步扩大Shibor在金融市场上的运用

Shibor自2007年初在银行间市场正式推出以来,其作为货币市场基准利率的作用逐渐得到充分的发挥。文章介绍了Shibor在各类金融产品（如浮息金融债、企业债、金融衍生品、票据贴现业务等）以及银行内部定价机制中日益广泛的运用,指出了当前制约Shibor发展的主要问题,并从提高Shibor可交易性、理顺同业拆借业务框架等方面就推进Shibor建设提出建议。     

Asymptotic arbitrage in large financial markets

A large financial market is described by a sequence of standard general models of continuous trading. It turns out that the absence of asymptotic arbitrage of the first kind is equivalent to the contiguity of sequence of objective probabilities with respect to the sequence of upper envelopes of equivalent martingale measures, while absence of asymptotic arbitrage of the second kind is equivalent to the contiguity of the sequence of lower envelopes of equivalent martingale measures with respect to the sequence of objective probabilities. We express criteria of contiguity in terms of the Hellinger processes. As examples, we study a large market with asset prices given by linear stochastic equations which may have random volatilities, the Ross Arbitrage Pricing Model, and a discrete-time model with two assets and infinite horizon. The suggested theory can be considered as a natural extension of Arbirage Pricing Theory covering the continuous as well as the discrete time case.     

Equilibrium dominance in experimental financial markets

We examine the predictive power of equilibrium dominance inexperimental markets where firms with investment opportunitieshave an informational advantage over potential investors andare permitted to purchase a money-burning signal. Equilibriumdominance often fails to predict well when a Pareto-superiorsequential equilibrium is also available. Instead, equilibriumselection appears to be related to the potential earnings ofa more valuable firm that can signal its type successfully bydefecting from the sequential equilibrium.     

Money and liquidity in financial markets

We argue that there is a connection between the interbank market for liquidity and the broader financial markets, which has its basis in demand for liquidity by banks. Tightness in the market for liquidity leads banks to engage in what we term “liquidity pull-back,” which involves selling financial assets either by banks directly or by levered investors. Empirical tests on the stock market are supportive. Tighter interbank markets are associated with relatively more volume in more liquid stocks; selling pressure, especially in more liquid stocks; and transitory negative returns. We control for market-wide uncertainty and in the process also contribute to the literature on portfolio rebalancing. Our general point is that money matters in financial markets.     

Information transfers and learning in financial markets: Evidence from short selling around insider sales

We document significant increases in short positions on days when company insiders sell their firms’ shares. Short selling increases before insider sales are publicly reported and often before insiders finish selling. Furthermore, the magnitude of short selling activity is consistent with short sellers’ knowledge of the insider’s rank (e.g., CEO, CFO, or a lower-ranked manager) and with knowledge of the unobservable size of the insider’s trading position. We show that short sellers’ superior timing is consistent with (i) monitoring of order flow and (ii) obtaining price-relevant information from brokerages that execute insider sales. Some of our results extend to insider purchases.     

Credit markets and financial information

The last decade has seen rapid growth in trading of credit instruments on secondary markets. The ensuing availability of a rich set of credit market data has created a novel environment for testing a variety of financial economic theories. In this discussion, we provide a simple framework for linking asset pricing research using equity and credit market data and offer some suggestions for future archival empirical research aiming to establish relations between financial information and credit markets. Credit instruments are intrinsically linked to equity instruments. The strength of this link varies temporally and cross-sectionally in measurable ways that can, and should be, used to guide future empirical research linking information to credit markets.     

2010年国际金融市场运行综述

2010年,美元对欧元、英镑先升后降,总体走强,但对日元贬值幅度较大;美元、欧元和英镑短期利率上升,日元短期利率下降;主要国家中长期国债收益率探底后小幅回升,总体降幅较大;主要股指振荡上涨。     

2011年国际金融市场运行综述

2011年,美元指数先跌后升;美元、欧元和英镑短期利率上升,日元短期利率基本走平;主要国家中长期国债收益率先升后降;全球主要股指先升后降。     

2013年国际金融市场运行综述

2013年,美元指数先升后降,总体持平。美元、日元短期利率下降,欧元、英镑短期利率上升。主要国家中长期国债收益率大幅上涨,但日本国债收益率有所下降。全球主要股指大幅上涨。     

2012年国际金融市场运行综述

2012年,美元指数总体小幅走低,年中一度走高;主要货币短期利率明显下降;主要发达国家中长期国债收益率总体下降;主要股指大幅上涨。     

2010年2月国际金融市场运行综述

2010年2月,受欧洲主权债务问题影响,市场避险情绪升温,美元对欧元、英镑走强,对日元走弱。因市场预期欧央行、日本银行和美联储将继续保持较为宽松的货币政策,英国可能率先加息,美元、欧元、日元短期利率基本走平,英镑短期利率微升。美国、英国、德国中长期国债收益率先升后降,日本中长期国债收益率下降。全球主要股指先跌后涨。     

2010年8月国际金融市场运行综述

2010年8月,美国公布的多数经济数据表现疲弱,显示其经济复苏步伐明显放缓,市场避险需求上升。受此影响,美元对欧元、英镑走强,但对日元走弱。美元短期利率下降,欧元、英镑和日元短期利率基本走平。主要国家中长期国债收益率明显下降。全球主要股指下跌。     

2011年11月国际金融市场运行综述

2011年11月,美元指数走高;美元、英镑短期利率上升,欧元短期利率下降,日元短期利率基本持平;美、英中长期国债收益率走低,德、日中长期国债收益率走高;全球主要股指呈“N”型走势,总体走低。