Quantitative Finance

Based on 1-minute price changes recorded since year 2012, the fluctuation properties of the rapidly-emerging Bitcoin (BTC) market are assessed over chosen sub-periods, in terms of return distributions, volatility autocorrelation, Hurst exponents and multiscaling effects. The findings are compared to the stylized facts of mature world markets. While early trading was affected by system-specific irregularities, it is found that over the months preceding Apr 2018 all these statistical indicators approach the features hallmarking maturity. This can be taken as an indication that the Bitcoin market, and possibly other cryptocurrencies, carry concrete potential of imminently becoming a regular market, alternative to the foreign exchange (Forex). Since high-frequency price data are available since the beginning of trading, the Bitcoin offers a unique window into the statistical characteristics of a market maturation trajectory.

The efficient market hypothesis has been considered one of the most controversial arguments in finance, with the academia divided between who claims the impossibility of beating the market and who believes that it is possible to gain over the average profits. If the hypothesis holds, it means, as suggested by Burton Malkiel, that a blindfolded monkey selecting stocks by throwing darts at a newspaper's financial pages could perform as well as a financial analyst, or even better. In this paper we use a novel approach, based on confidence intervals for proportions, to assess the degree of inefficiency in the S&P 500 Index components concluding that several stocks are inefficient: we estimated the proportion of inefficient stocks in the index to be between 12.13% and 27.87%. This supports other studies proving that a financial analyst, probably, is a better investor than a blindfolded monkey.

Regulators require financial institutions to estimate counterparty default risks from liquid CDS quotes for the valuation and risk management of OTC derivatives. However, the vast majority of counterparties do not have liquid CDS quotes and need proxy CDS rates. Existing methods cannot account for counterparty-specific default risks; we propose to construct proxy CDS rates by associating to illiquid counterparty liquid CDS Proxy based on Machine Learning Techniques. After testing 156 classifiers from 8 most popular classifier families, we found that some classifiers achieve highly satisfactory accuracy rates. Furthermore, we have rank-ordered the performances and investigated performance variations amongst and within the 8 classifier families. This paper is, to the best of our knowledge, the first systematic study of CDS Proxy construction by Machine Learning techniques, and the first systematic classifier comparison study based entirely on financial market data. Its findings both confirm and contrast existing classifier performance literature. Given the typically highly correlated nature of financial data, we investigated the impact of correlation on classifier performance. The techniques used in this paper should be of interest for financial institutions seeking a CDS Proxy method, and can serve for proxy construction for other financial variables. Some directions for future research are indicated.

The novel of coronavirus (COVID-19) has suddenly and abruptly changed the world as we knew at the start of the 3rd decade of the 21st century. Particularly, COVID-19 pandemic has negatively affected financial econometrics and stock markets across the globe. Artificial Intelligence (AI) and Machine Learning (ML)-based prediction models, especially Deep Neural Network (DNN) architectures, have the potential to act as a key enabling factor to reduce the adverse effects of the COVID-19 pandemic and future possible ones on financial markets. In this regard, first, a unique COVID-19 related PRIce MOvement prediction (COVID19 PRIMO) dataset is introduced in this paper, which incorporates effects of social media trends related to COVID-19 on stock market price movements. Afterwards, a novel hybrid and parallel DNN-based framework is proposed that integrates different and diversified learning architectures. Referred to as the COVID-19 adopted Hybrid and Parallel deep fusion framework for Stock price Movement Prediction (COVID19-HPSMP), innovative fusion strategies are used to combine scattered social media news related to COVID-19 with historical mark data. The proposed COVID19-HPSMP consists of two parallel paths (hence hybrid), one based on Convolutional Neural Network (CNN) with Local/Global Attention modules, and one integrated CNN and Bi-directional Long Short term Memory (BLSTM) path. The two parallel paths are followed by a multilayer fusion layer acting as a fusion centre that combines localized features. Performance evaluations are performed based on the introduced COVID19 PRIMO dataset illustrating superior performance of the proposed framework.

The cryptocurrency market is unique on many levels: Very volatile, frequently changing market structure, emerging and vanishing of cryptocurrencies on a daily level. Following its development became a difficult task with the success of cryptocurrencies (CCs) other than Bitcoin. For fiat currency markets, the IMF offers the index SDR and, prior to the EUR, the ECU existed, which was an index representing the development of European currencies. Index providers decide on a fixed number of index constituents which will represent the market segment. It is a challenge to fix a number and develop rules for the constituents in view of the market changes. In the frequently changing CC market, this challenge is even more severe. A method relying on the AIC is proposed to quickly react to market changes and therefore enable us to create an index, referred to as CRIX, for the cryptocurrency market. CRIX is chosen by model selection such that it represents the market well to enable each interested party studying economic questions in this market and to invest into the market. The diversified nature of the CC market makes the inclusion of altcoins in the index product critical to improve tracking performance. We have shown that assigning optimal weights to altcoins helps to reduce the tracking errors of a CC portfolio, despite the fact that their market cap is much smaller relative to Bitcoin. The codes used here are available via this http URL.

While Post-Earnings-Announcement Drift (PEAD) is one of the most studied stock market anomalies, the current literature is often limited in explaining this phenomenon by a small number of factors using simpler regression methods. In this paper, we use a machine learning based approach instead, and aim to capture the PEAD dynamics using data from a large group of stocks and a wide range of both fundamental and technical factors. Our model is built around the Extreme Gradient Boosting (XGBoost) and uses a long list of engineered input features based on quarterly financial announcement data from 1,106 companies in the Russell 1000 index between 1997 and 2018. We perform numerous experiments on PEAD predictions and analysis and have the following contributions to the literature. First, we show how Post-Earnings-Announcement Drift can be analysed using machine learning methods and demonstrate such methods' prowess in producing credible forecasting on the drift direction. It is the first time PEAD dynamics are studied using XGBoost. We show that the drift direction is in fact driven by different factors for stocks from different industrial sectors and in different quarters and XGBoost is effective in understanding the changing drivers. Second, we show that an XGBoost well optimised by a Genetic Algorithm can help allocate out-of-sample stocks to form portfolios with higher positive returns to long and portfolios with lower negative returns to short, a finding that could be adopted in the process of developing market neutral strategies. Third, we show how theoretical event-driven stock strategies have to grapple with ever changing market prices in reality, reducing their effectiveness. We present a tactic to remedy the difficulty of buying into a moving market when dealing with PEAD signals.

In a previous analysis the problem of "zero-inflated" time data (caused by high frequency trading in the electronic order book) was handled by left-truncating the inter-arrival times. We demonstrated, using rigorous statistical methods, that the Weibull distribution describes the corresponding stochastic dynamics for all inter-arrival time differences except in the region near zero. However, since the truncated Weibull distribution was not able to describe the huge "zero-inflated" probability mass in the neighbourhood of zero (making up approximately 50\% of the data for limit orders), it became clear that the entire probability distribution is a mixture distribution of which the Weibull distribution is a significant part. Here we use a censored EM algorithm to analyse data for the difference of the arrival times of market orders, which usually have a much lower percentage of zero inflation, for four selected stocks trading on the London Stock Exchange.

A major impact of globalization has been the information flow across the financial markets rendering them vulnerable to financial contagion. Research has focused on network analysis techniques to understand the extent and nature of such information flow. It is now an established fact that a stock market crash in one country can have a serious impact on other markets across the globe. It follows that such crashes or critical regimes will affect the network dynamics of the global financial markets. In this paper, we use sequential change point detection in dynamic networks to detect changes in the network characteristics of thirteen stock markets across the globe. Our method helps us to detect changes in network behavior across all known stock market crashes during the period of study. In most of the cases, we can detect a change in the network characteristics prior to crash. Our work thus opens the possibility of using this technique to create a warning bell for critical regimes in financial markets.

The bitcoin price has surged in recent years and it has also exhibited phases of rapid decay. In this paper we address the question to what extent this novel cryptocurrency market can be viewed as a classic or semi-efficient market. Novel and robust tools for estimation of multi-fractal properties are used to show that the bitcoin price exhibits a very interesting multi-scale correlation structure. This structure can be described by a power-law behavior of the variances of the returns as functions of time increments and it can be characterized by two parameters, the volatility and the Hurst exponent. These power-law parameters, however, vary in time. A new notion of generalized Hurst exponent is introduced which allows us to check if the multi-fractal character of the underlying signal is well captured. It is moreover shown how the monitoring of the power-law parameters can be used to identify regime shifts for the bitcoin price. A novel technique for identifying the regimes switches based on a goodness of fit of the local power-law parameters is presented. It automatically detects dates associated with some known events in the bitcoin market place. A very surprising result is moreover that, despite the wild ride of the bitcoin price in recent years and its multi-fractal and non-stationary character, this price has both local power-law behaviors and a very orderly correlation structure when it is observed on its entire period of existence.

The recent emergence of cryptocurrencies such as Bitcoin and Ethereum has posed possible alternatives to global payments as well as financial assets around the globe, making investors and financial regulators aware of the importance of modeling them correctly. The Levy's stable distribution is one of the attractive distributions that well describes the fat tails and scaling phenomena in economic systems. In this paper, we show that the behaviors of price fluctuations in emerging cryptocurrency markets can be characterized by a non-Gaussian Levy's stable distribution with α≃1.4 under certain conditions on time intervals ranging roughly from 30 minutes to 4 hours. Our arguments are developed under quantitative valuation defined as a distance function using the Parseval's relation in addition to the theoretical background of the General Central Limit Theorem (GCLT). We also discuss the fit with the Levy's stable distribution compared to the fit with other distributions by employing the method based on likelihood ratios. Our approach can be extended for further analysis of statistical properties and contribute to developing proper applications for financial modeling.