Predicting the Risk of Bankruptcy for ARO Stock
Abstract
In the last several decades, many researchers have been focused on finding effective experimental methods to predict stocks with tendency of bankrupt. Recent financial crisis has caused extensive world-wide economic damages, predicting bankruptcy before it happens could help investors avoid large losses. In this article, by observing the market dynamics of its stock price and trading volume, we estimate the risk of bankruptcy of Aeropostale (ARO). GARCH and EGARCH series models with normal distribution and t-student distribution are used to estimate the volatilities and value-atrisk (VaR) of ARO stock. By analyzing the VaR, we conclude that there is a high probability that the company will be facing bankruptcy in the near future. Moreover, our study shows that the asymmetric EGARCH model with t-student distribution eventually is a better choice to predict the behavior of this stock.
Keywords
Download Options
Introduction
Bankruptcy forecasting has been an open challenging problem for financial analysts. The most recent financial crisis was caused by sub-prime mortgages written in 2006, which mainly contributed to Lehman Brother’s bankruptcy in September 2008. The bankruptcies of many other corporations at that time also resulted in substantial losses to many investors and hedge funds. The general consensus is that if one could accurately predict bankruptcy, and identify a characteristic behavior exhibited by a stock before bankruptcy, it would help investors avoid certain large losses. Thus bankruptcy prediction is a topic of great interest, not only to investors and hedge funds, but also to researchers across a wide range of fields. In this paper, we investigate the risk of Aeropostale, Inc. (known as ARO), which is an American apparel retailer, principally targeting teenagers and young people. The company operates 773 Aeropostale stores in the U.S. and about 61 stores in Canada. The company’s chief competitors Forever 21 Inc. and American Eagle offer just as fashionable clothing at much cheaper prices. Plus, the overall teenage fashion styles have changed, while Aeropostale’s has not. The company continues to produce clothing that displays the brand’s name, which has long gone out of style. Aeropostale has served up 11 straight quarters of losses, shrinking cash at the end of the second quarter to stand at $86 million, down from $151 million at the start of 2015. ARO stock has lost more than 60% in the last 12 months.
Many researchers and analysts have attempted to develop models for predicting corporate bankruptcy, but most of these models depend on the availability of detailed internal financial information or the financial statement about the corporation, such as Altman (1968) and Ohlson (1980). In general the financial statement has both balance sheet and income statement, which is often difficult to obtain for general investors, except possibly some large hedge funds. A commonly used financial tool is the Z-Score, which was developed in 1968 by Edward I. Altman, as a quantitative balance-sheet method of determining the financial health of a company. However as pointed by Altman (2002), the Z-Score was not intended to be used on non-manufacturing companies. Based on latest financial disclosure using the Z-Score calculation, Aeropostale Inc. only has probability of bankruptcy (Z-Score) of 34.58%. This is somewhat misleading for the investors. For more details, see, https://www.macroaxis.com/invest/ratio/ARO–Probability-Of-Bankruptcy.
Since all investors have access to historical data of daily stock prices and trading volumes, it would be more beneficial if one could predict a corporation’s risk of bankruptcy by observing the market dynamics of its stock price. The goal of our study is to develop an early warning system to forecast the time of bankruptcy based on statistical analysis of the stock dynamics, rather than corporate internal financial information. Based on the daily closing share prices and trading volume of ARO, we use statistical properties to analyze ARO stocks to discover the tendency of stocks moving to bankruptcy.
Conclusion
Our statistical studies discover that the ARO stock has a high probability of approaching bankruptcy. According to recent work by Li etc.(2011), one of the most significant features in the distribution of returns: pre-bankrupt stocks are more likely to have larger daily returns (both positive and negative) than stocks that do not become bankrupt. In other words, prebankrupt stocks have larger daily price fluctuations. According to the statistical quantities given in Table 1, we know that the difference is bigger for negative returns than positive returns, indicating the falling stock price preceding a bankruptcy. Indeed the closer the day of bankruptcy approaches, the greater the possibility for these dramatic price changes.
A second major feature pointed out in Li etc.(2011) is that the pre-bankrupt stocks experience a stronger correlation between volatility and volume. Previous research has shown that volatility and volume exhibit a positive correlation, meaning that large changes in stock price are often accompanied by large changes in trading volume. This is confirmed by comparing Figure 1 and Figure 3, as we can see that both the log returns and the trading volume have large fluctuations in 2015. This is pretty odd situation which is obviously distinguishes ARO from healthy stocks. For healthy stocks, if the mean of return is negative, the trading volume should decrease. This phenomenon is also evidence that many insiders are selling a large amount of shares and short sales have increased significantly, which is mainly due to some inter-information on the potential bankruptcy of the company. We also find the asymmetric EGARCH Model with t-student distribution should be a suitable tool to predict the volatilities of ARO, which indicates that the market dynamics of the stock is mainly impacted by some “bad news” or certain negative information.
Our empirical study also shows that the VaR and the stock price are strongly correlated. In Fig.11, we plot the time series plot of daily close price in blue with VaR(95%) of ARO in red which are shifted by 20 units up. One can see that these two curves have similar up/downward trends in last few years.
Consequently our statistical investigation of the historical data of ARO indicates that this stock has a strong tendency approaching bankruptcy. Therefore we suggest investors should avoid investing in ARO stocks