Predicting Intraday Trading Volume and Volume Percentages

This article discusses recent techniques and results in the area of forecasting intraday volume and intraday volume percentages. By exploring ways to predict volume, the authors seek to improve the performance of trading algorithms, many of which depend upon the volume that will trade while the order is active. Traditionally, algorithms use historical averages to predict volume over the lifetime of an order. The authors show that improving the prediction of volume boosts the performance of algorithms.

Creating Dynamic Pretrade Models: Beyond the Black Box

We provide a framework for investment managers to create dynamic pretrade models. The approach helps market participants shed light on vendor black-box models that often do not provide any transparency into the model’s functional form or working mechanics. In addition, this allows portfolio managers to create consensus estimates based on their own expectations, such as forecasted liquidity and volatility, and to incorporate firm proprietary alpha estimates into the solution. These techniques allow managers to reduce overdependency on any one black-box model, incorporate costs into the stock selection and portfolio optimization phase of the investment cycle, and perform “what-if” and sensitivity analyses without the risk of information leakage to any outside party or vendor.

COMMENTARY: Volatility Forecasting

This paper provides a perspective on volatility forecasting. The basic idea is that a number of factors are leading to volatility having a lower baseline expected value than in prior years. These factors include lower earnings uncertainty, greater market efficiency, better market-marking, and the fact that volatility trading itself tends to reduce volatility.

Five Myths About Listed Trading

ECNs and other electronic venues familiar to Nasdaq traders are beginning to gain traction on the listed side. These innovations are causing investors to reevaluate the meaning of “best execution” and other traditional views about the listed marketplace. The author reviews five such views and concludes that they are myths, not truths. To properly evaluate best execution, careful investors will similarly test doctrinaire notions of listed trading.

Cluster Analysis for Evaluating Trading Strategies

In this article, we introduce a new methodology to empirically identify the primary strategies used by a trader using only post-trade fill data. To do this, we apply a well-established statistical clustering technique called k-means to a sample of progress charts, representing the portion of the order completed by each point in the day as a measure of a trade’s aggressiveness. Our methodology identifies the primary strategies used by a trader and determines which strategy the trader used for each order in the sample. Having identified the strategy used for each order, trading cost analysis can be performed by strategy. We also discuss ways to exploit this technique to characterize trader behavior, assess trader performance, and suggest the appropriate benchmarks for each distinct trading strategy.

COMMENTARY: Beyond the Black Box Revisited: Algorithmic Trading and TCA Analysis Using Excel

In this paper we revisit techniques from “Creating Dynamic Pre-Trade Models: Beyond the Black Box” (Kissell, 2011) which was awarded The Journal of Trading’s Best Paper of the Year Award in 2011. We provide investors a pre-trade of pre-trade modeling technique that can be used to decipher broker and vendor models, and to calibrate a customized investor specific market impact model. We also provide a suite of Excel TCA Add-In functions that can incorporate investor specific market impact parameters and allow investors to perform TCA analysis on their own desktops within Excel, and with the added level of security and comfort that their investment decision process will not be reverse engineered because they do not need to upload or transmit any of their proprietary information and valuable trade information to a third-party website or API for analysis. Techniques in this paper enable investors to create their own customized TCA analyses within Excel to assist with both trading decisions and portfolio analysis and optimization.

COMMENTARY: Dark Pools, Fragmented Markets, and the Quality of Price Discovery: Commentary

This commentary is on a paper published in 2010. Few would wish to roll the markets back to where they were eight years ago, but have the issues that were debated then been adequately resolved? Are today’s markets acceptably efficient? Can we relax about market quality? My answer to each of these is “no.” What I wrote in 2010, I stand by now. Along with revisiting my previous discussion on dark pools, fragmentation, price discovery, and liquidity, this commentary presents my newer thoughts concerning the definition of the term “liquidity,” and the existence of an illiquidity premium.

COMMENTARY: A Market Structure That Fits the Needs of Portfolio Managers

Trading “these” securities for “those” (portfolio trades) can be expensive if done through our current continuous markets. This article compares a broker-implemented blind bid solution to this problem in a continuous market setting versus a combined value computerized call market that maximizes available liquidity to create balanced trades between such lists. The technology is known: combined value markets are in use today servicing markets in logistics contracts, emissions permits, spectrum licenses, and aerospace procurement. Should not financial concerns, such as custodial banks, be currently offering such services to their clients?

Market Structure Matters

Richard Roll observed that continuous markets are more volatile than other market structures. If it is true that continuous markets induce volatility, then unless we change that market structure, we will continue to be plagued with sporadic bursts of nonfunctional, uninformative volatility. This article looks to the underlying reasons and suggests a more serviceable market structure.

Phantom Liquidity and High-Frequency Quoting

This article examines every NASDAQ ITCH feed message for S&P 500 Index stocks for 2012 and identifies clusters of extremely high and extremely low limit-order cancellation activity. The authors find results consistent with the idea that cancel clusters are the result of high-frequency traders jockeying for queue position and reacting to information to establish a new price level. Furthermore, few trades seem to be executed during cancel clusters or even immediately after them. Low cancellation activity seems to be markedly different, with many level changes all caused by executions. The results are consistent with high-frequency trading firms behaving as agents who bring efficiency to the market without the need to have executions at intermediate prices. The authors also discuss the misconception that investors and low-frequency traders are synonymous and its implications for policy given these results.