Abstract

VPIN is a tool designed to predict extreme events like flash crashes. Some concerns have been raised about its reliability. In this chapter we assess VPIN prediction quality (precision and recall rates) of extreme volatility events including its sensitivity to the starting point of computation in a given data set. We benchmark the results with the ones of a "naive classifier." The test data used in this study contains 5.6 year's worth of trading data of the five most liquid futures contracts of this time period. We found that VPIN has poor "flash crash" prediction power with the traditional 0.99 decision threshold. Increasing the decision threshold does not significantly improve overall prediction quality. Nevertheless we found VPIN has a more interesting predictive power for flash events of lower amplitude. Finally, we found that, for practice, the last bar price structure is the least sensitive to the starting point of computation.

Keywords: high-frequency data, probability of informed trading, VPIN, liquidity, flow toxicity, volume imbalance, flash crash JEL codes: C02, D52, D53, G14, G23

#### 1. Introduction

#### 1.1 Main study purpose

Easley et al. [1] designed a tool, nicknamed volume-synchronized probability of informed trading (VPIN), with the aim to predict flash crashes. It appeared it could predict the "flash crash" of May 6, 2010, a few hours before it happened [2]. A lot of papers were published [3–5], and it was proposed to use it for regulation through a VPIN contract [2, 6]. However, critics pointed out some flaws, questioning its reliability [7–11] but without providing a quantitative evaluation of the prediction quality (e.g., in terms of precision and recall rates). In this study, we design a framework to detect flash crashes and thereby assess the behavior of the VPIN tool enabling as well as comparing and benchmarking with other predictive algorithms.

#### 1.2 Motivation

The amount of trading data has exploded in finance thanks to the continuing progress of high-frequency techniques. It constrains practitioners to use more and more state-of-the-art algorithms to deal with this overwhelming amount of information. Computers and algorithms are more and more efficient, but still

decision-making is highly dependent on both the quantity and the quality of information. Thus, errors and speculations that can make the financial market toxic, i.e., conducive to crashes, are possible. Examples in the past, such as the "flash crash" of May 6, 2010, have shown that this new paradigm in finance has made it possible to introduce a new kind of crashes characterized by their suddenness. Such quick crashes seem dangerous because of a kind of inherent unpredictability. However, predictive models to model this new framework do exist.

### 1.3 Model

Easley et al. [12] designed a model of the high-frequency financial market based on flows of informed and uninformed traders. They showed that information is a key parameter of the spread between ask and bid of prices. The model works as follows. Each day, general conditions and circumstances may or may not result in events that can help predict the evolution of the price of a future. More precisely, for each day, nature decides whether or not there is an event that can help predict the evolution of the price of a future. This is modeled with a Bernoulli law of parameter α. If an event occurs, nature also decides with a Bernoulli law of parameter δ if this event is a low signal. With these conditions, buys and sells for this future come then from flows of informed and uninformed traders. They are modeled by Poisson processes of respective parameters μ and ϵ. This framework can be summarized by the following tree in Figure 1 [13].

The whole trading process studied is thus a mixture of Poisson processes. It enabled authors to compute ask and bid and then the spread. They showed that for reasonable cases the spread is linearly linked with the following probability they named probability of informed trading (PIN) [12]:

$$\text{PIN} = \frac{a\mu}{a\mu + 2\epsilon}. \tag{1}$$

with a new formula. The approximated version of PIN was then called the

value, although the proposed formula is close [15, 16]. More generally, all these critics have pointed out that:

• First, it is not obvious how one should use VPIN.

• Third, the study lacks objective benchmark.

for trading or regulation). That's why:

starting point of the data set.

happened [2].

An Assessment of the Prediction Quality of VPIN DOI: http://dx.doi.org/10.5772/intechopen.86532

reliable.

1.4 Goal

1.5 Plan

55

data set (Section 4).

volume-synchronized probability of informed trading (VPIN). It appeared that this new tool could predict the "flash crash" of May 6, 2010, a few hours before it

Nevertheless, the model has received a lot of critics. For example, Andersen and Bondarenko have shown [7] that VPIN is quite sensitive to the starting point of when one starts computing VPIN on a data set. It indeed questions VPIN prediction quality. Moreover, they have also shown that VPIN is sensitive to other parameters, such as the trade classification rule used [8] or how one defines the average daily volume of trades [9]. Changing the classification rule may drastically change VPIN behavior [9]. Pöppe et al. have reached the same conclusions with a different approach. Using a different classification rule can change VPIN prediction power toward a crash (in their paper a German blue-chip stock [11]). Besides, controlling ex ante parameters seems to give poorer prediction quality [8, 9]. This point has also been checked by Abad et al. [10]. Controlling ex ante realized volatility, and trading intensity, as did Andersen and Bondarenko [9], prediction quality seems to vanish. More deeply, they have also underlined that it is not obvious how one should define a VPIN prediction, analyzing more precisely toxic and nontoxic halts, as well as toxic events. Furthermore, Torben G. Andersen and Oleg Bondarenko interpret VPIN as being too sensitive to trading intensity. They have also explained that VPIN metric is sometimes unexpectedly correlated with other usual ones (such as VIX or RV) [7, 8]. More recently, it has been shown theoretically that the volume-clock paradigm of VPIN framework does not enable to really approximate fully the PIN

• Second, prediction quality has not been studied sufficiently to assess it as being

The purpose of this chapter is to quantify the prediction quality of VPIN in order to enable practitioners to assess whether or not it can be used in the real world (e.g.,

• First, we want to design a proper framework to compute precision and recall rates as well as prediction length of VPIN. This will be possible by providing a

• Second, we want to study through this framework how sensitive VPIN is to the

In the following, we first recall VPIN model and propose a definition for flash crashes (Section 2). Second, we assess within this framework VPIN prediction quality (Section 3). Finally, we assess VPIN sensitivity to the starting point of the

formal definition of flash crashes. To be more precise, we will use the

maximum of intermediate return (MIR) [5] to define it.

Later, Easley et al. [2] designed a new framework to easily compute this probability. Indeed PIN numbers come from a parametrized framework, and one does not have access to all these parameters. They showed however that PIN can be well approximated through a volume-clock paradigm [14], thanks to data of futures

Figure 1. A tree summarizing the trading process.

An Assessment of the Prediction Quality of VPIN DOI: http://dx.doi.org/10.5772/intechopen.86532

decision-making is highly dependent on both the quantity and the quality of information. Thus, errors and speculations that can make the financial market toxic, i.e., conducive to crashes, are possible. Examples in the past, such as the "flash crash" of May 6, 2010, have shown that this new paradigm in finance has made it possible to introduce a new kind of crashes characterized by their suddenness. Such quick crashes seem dangerous because of a kind of inherent unpredictability.

Easley et al. [12] designed a model of the high-frequency financial market based on flows of informed and uninformed traders. They showed that information is a key parameter of the spread between ask and bid of prices. The model works as follows. Each day, general conditions and circumstances may or may not result in events that can help predict the evolution of the price of a future. More precisely, for each day, nature decides whether or not there is an event that can help predict the evolution of the price of a future. This is modeled with a Bernoulli law of parameter α. If an event occurs, nature also decides with a Bernoulli law of parameter δ if this event is a low signal. With these conditions, buys and sells for this future come then from flows of informed and uninformed traders. They are modeled by Poisson processes of respective parameters μ and ϵ. This framework can

The whole trading process studied is thus a mixture of Poisson processes. It enabled authors to compute ask and bid and then the spread. They showed that for reasonable cases the spread is linearly linked with the following probability they

PIN <sup>¼</sup> αμ

αμ þ 2ϵ

Later, Easley et al. [2] designed a new framework to easily compute this probability. Indeed PIN numbers come from a parametrized framework, and one does not have access to all these parameters. They showed however that PIN can be well approximated through a volume-clock paradigm [14], thanks to data of futures

: (1)

However, predictive models to model this new framework do exist.

Advanced Analytics and Artificial Intelligence Applications

be summarized by the following tree in Figure 1 [13].

named probability of informed trading (PIN) [12]:

1.3 Model

Figure 1.

54

A tree summarizing the trading process.

with a new formula. The approximated version of PIN was then called the volume-synchronized probability of informed trading (VPIN). It appeared that this new tool could predict the "flash crash" of May 6, 2010, a few hours before it happened [2].

Nevertheless, the model has received a lot of critics. For example, Andersen and Bondarenko have shown [7] that VPIN is quite sensitive to the starting point of when one starts computing VPIN on a data set. It indeed questions VPIN prediction quality. Moreover, they have also shown that VPIN is sensitive to other parameters, such as the trade classification rule used [8] or how one defines the average daily volume of trades [9]. Changing the classification rule may drastically change VPIN behavior [9]. Pöppe et al. have reached the same conclusions with a different approach. Using a different classification rule can change VPIN prediction power toward a crash (in their paper a German blue-chip stock [11]). Besides, controlling ex ante parameters seems to give poorer prediction quality [8, 9]. This point has also been checked by Abad et al. [10]. Controlling ex ante realized volatility, and trading intensity, as did Andersen and Bondarenko [9], prediction quality seems to vanish. More deeply, they have also underlined that it is not obvious how one should define a VPIN prediction, analyzing more precisely toxic and nontoxic halts, as well as toxic events. Furthermore, Torben G. Andersen and Oleg Bondarenko interpret VPIN as being too sensitive to trading intensity. They have also explained that VPIN metric is sometimes unexpectedly correlated with other usual ones (such as VIX or RV) [7, 8]. More recently, it has been shown theoretically that the volume-clock paradigm of VPIN framework does not enable to really approximate fully the PIN value, although the proposed formula is close [15, 16].

More generally, all these critics have pointed out that:


#### 1.4 Goal

The purpose of this chapter is to quantify the prediction quality of VPIN in order to enable practitioners to assess whether or not it can be used in the real world (e.g., for trading or regulation). That's why:


#### 1.5 Plan

In the following, we first recall VPIN model and propose a definition for flash crashes (Section 2). Second, we assess within this framework VPIN prediction quality (Section 3). Finally, we assess VPIN sensitivity to the starting point of the data set (Section 4).
