Financial Econometrics and Empirical Market Microstructure

AIG Case Study Using FNA HeavyTails™ Outlier Monitor

FNA’s recently launched HeavyTails application is network implementation of the Adaptive Stress Testing framework. The initial focus of HeavyTails is to monitor global market outliers.[25]

AIG’s collapse during the U. S. subprime crisis is a classic early warning case study. As policy makers wrestled with the implosion of Lehman Brothers, they were blindsided by AIG, which would require a record $182 bn bailout. Policy makers realized AIG was on the precipice only “days before its imminent collapse” recounts Phil Angelides, Chair, Financial Crisis Inquiry Commission.

When analyzing the unusual price action of AIG stock, it becomes evident that major market participants suspected AIG’s precarious state for many months. Outlier based early warning signals would have been invaluable to policy makers in prioritizing their focus.

Figure 21 shows the Minimum Spanning Tree (Mantegna 1999) correlation network of major financial institutions on September 15, 2008, the day Lehman defaulted and AIG’s shares collapsed. Outliers are highlighted in red, and ranked by size. Lehman was the biggest surprise, as a 3.92 standard deviation (sd) loss, followed by AIG, a 3.68 sd surprise.


Fig. 21 September 15, 2008: Banking HeavyTails Network Graph. Source: FNA HeavyTails

AIG exhibited exceptional outlier activity leading up to the crisis. Figure 22 shows that there were 14 negative 95 % Confidence VaR outliers in the previous 100 trading days, almost triple the expected 5 % level. The probability of seeing 14 or more negative 5 % outliers in 100 days (assuming IID) is 0.0004632734.

AIG’s negative outliers were also exceptional when compared with other finan­cial institutions. Table 3 ranks major institutions by number of negative VaR outliers as of market close on September 15, 2008.

AIG’s unusual level of negative outliers commenced almost a year before its eventual collapse. In Fig. 23 we can see that AIG’s stock experienced a —3.1 sd outlier (12.5 % decline) on February 11, 2008 as it announced “material accounting weakness” in its credit derivative portfolio. Again, outliers provided early warning, as AIG had been running at 9 % downside outliers vs. 3 % upside in 100 days as seen in Fig. 24. Notice AIG was the only major financial institution that experienced an outlier on that day.


Подпись: Fig. 23 AIG negative outlier February 11, 2008. Source: FNA HeavyTails

Table 3 VaR outliers as of September 15, 2008

Добавить комментарий

Financial Econometrics and Empirical Market Microstructure

Modeling Financial Market Using Percolation Theory

Anastasiya Byachkova and Artem Simonov Abstract Econophysics is a relatively new discipline. It is one of the most interesting and promising trends in modeling complex economic systems such as financial …

Multifractal Formalism for Stochastic Processes

Original definition of fractal was proposed by Mandelbrot with respect to sets. He defined fractal as a mathematical set with fractal dimension is strictly larger than its topological dimension (Mandelbrot …

Adaptive Learning

Risk management is a core discipline in a rapidly changing world. From finance to ecology, we face unprecedented systemic risks from increasingly coupled global systems. Non-linearities render long term predictions …

Как с нами связаться:

тел./факс +38 05235  77193 Бухгалтерия
+38 050 512 11 94 — гл. инженер-менеджер (продажи всего оборудования)

+38 050 457 13 30 — Рашид - продажи новинок
Схема проезда к производственному офису:
Схема проезда к МСД

Партнеры МСД

Контакты для заказов шлакоблочного оборудования:

+38 096 992 9559 Инна (вайбер, вацап, телеграм)
Эл. почта: