We conduct a comprehensive study of commonality in liquidity using intraday spread and depth data from 47 stock exchanges. We find that firm-level changes in liquidity are significantly influenced by exchange-level changes across most of the world’s stock exchanges. Emerging Asian exchanges have exceptionally strong commonality, while those of Latin America exhibit little if any commonality. After documenting the pervasive role of commonality within individual exchanges, we examine commonality across exchanges. We find evidence of a distinct, global component in bid-ask spreads and depths. Local (exchange-level) sources of commonality represent roughly 39% of the firm’s total commonality in liquidity, while global sources contribute an additional 19%. We also investigate potential sources of exchange-level and global commonality. We show that commonality is driven by both domestic and U.S. macroeconomic announcements.
Many government data, such as sensitive information on individuals' taxes, income, employment, or health, are available only to accredited users within a secure computing environment. Though they can be cumbersome to access, such microdata can allow researchers to pursue questions that could not be addressed with only public data (1). However, researchers using confidential data are inexorably challenged with regard to research reproducibility (2). Empirical results cannot be easily reproduced by peers and journal referees, as access to the underpinning data are restricted. We describe an approach that allows researchers who analyze confidential data to signal the reproducibility of their research. It relies on a certification process conducted by a specialized agency accredited by the confidential-data producers and which can guarantee that the code and the data used by a researcher indeed produce the results reported in a scientific paper.
31 October 2017 in Journal of Financial and Quantitative Analysis
We present CoMargin, a new methodology to estimate collateral requirements in derivatives central counterparties (CCPs). CoMargin depends on both the tail risk of a given market participant and its interdependence with other participants. Our approach internalizes trading externalities and enhances the stability of CCPs, thus reducing systemic risk concerns. We assess our methodology using proprietary data from the Canadian Derivatives Clearing Corporation that include daily observations of the actual trading positions of all of its members from 2003 to 2011. We show that CoMargin outperforms existing margining systems by stabilizing the probability and minimizing the shortfall of simultaneous margin-exceeding losses.
11 September 2012 in Journal of Risk and Insurance
In this article, we discuss the contribution of machine learning techniques and new data sources (new data) to credit-risk modelling. Credit scoring was historically one of the first fields of application of machine learning techniques. Today, these techniques permit to exploit new sources of data made available by the digitalization of customer relationships and social networks. The combination of the emergence of new methodologies and new data has structurally changed the credit industry and favored the emergence of new players. First, we analyse the incremental contribution of machine learning techniques per se. We show that they lead to significant productivity gains but that the forecasting improvement remains modest. Second, we quantify the contribution of the "datadiversity", whether or not these new data are exploited through machine learning. It appears that some of these data contain weak signals that significantly improve the quality of the assessment of borrowers’ creditworthiness. At the microeconomic level, these new approaches promote financial inclusion and access to credit for the most vulnerable borrowers. However, machine learning applied to these data can also lead to severe biases and discrimination. Classification JEL : C10, C38, C55, G21, G29.