In automatic financial feature construction task, the state of the art technic leverages reverse polish expression to represent the features, then use genetic programming (GP) to conduct its evolution process. In this paper, we propose a new framework based on neural network, alpha discovery neural network (ADNN). In this work, we made several contributions. Firstly, in this task, we make full use of neural network's overwhelming advantage in feature extraction to construct highly informative features. Secondly, we use domain knowledge to design the object function, batch size, and sampling rules. Thirdly, we use pre-training to replace the GP's evolution process. According to neural network's universal approximation theorem, pre-training can conduct a more effective and explainable evolution process. Experiment shows that ADNN can remarkably produce more diversified and higher informative features than GP. Besides, ADNN can serve as a data augmentation algorithm. It further improves the the performance of financial features constructed by GP.

The global minimum-variance portfolio is a typical choice for investors because of its simplicity and broad applicability. Although it requires only one input, namely the covariance matrix of asset returns, estimating the optimal solution remains a challenge. In the presence of high-dimensionality in the data, the sample covariance estimator becomes ill-conditioned and leads to suboptimal portfolios out-of-sample. To address this issue, we review recently proposed efficient estimation methods for the covariance matrix and extend the literature by suggesting a multi-fold cross-validation technique for selecting the necessary tuning parameters within each method. Conducting an extensive empirical analysis with four datasets based on the S&P 500, we show that the data-driven choice of specific tuning parameters with the proposed cross-validation improves the out-of-sample performance of the global minimum-variance portfolio. In addition, we identify estimators that are strongly influenced by the choice of the tuning parameter and detect a clear relationship between the selection criterion within the cross-validation and the evaluated performance measure.

A new method for stochastic control based on neural networks and using randomisation of discrete random variables is proposed and applied to optimal stopping time problems. Numerical tests are done on the pricing of American and swing options. An extension to impulse control problems is described and applied to options hedging under fixed transaction costs. The proposed algorithms seem to be competitive with the best existing algorithms both in terms of precision and in terms of computation time.

Several proposals for the reform of the euro area advocate the creation of a market in synthetic securities backed by portfolios of sovereign bonds. Most debated are the so-called European Safe Bonds or ESBies proposed by (Brunnermeier et al. 2017). This paper provides a comprehensive quantitative analysis of such products. A key component of our contribution is a novel dynamic credit risk model which captures salient features of euro area sovereign CDS spreads and enables tractable modelling of default dependence amongst euro members. After successful calibration of our model to CDS spreads, we perform a thorough analysis of ESBies. We provide model-independent price bounds; we consider the expected loss as a function of model parameters and attachment points; we study the volatility of the credit spread of ESBies; and we discuss several approaches to assess the market risk of ESBies. Our analysis provides a fairly comprehensive picture of the risks associated with ESBies.

The main purpose of this study is to introduce a semi-classical model describing betting scenarios in which, at variance with conventional approaches, the payoff of the gambler is encoded into the internal degrees of freedom of a quantum memory element. In our scheme, we assume that the invested capital is explicitly associated with the free-energy (ergotropy) of a single mode of the electromagnetic radiation which, depending on the outcome of the betting, experiences attenuation or amplification processes which model losses and winning events. In particular, the evolution of the quantum memory results in a stochastic trajectory which we characterize within the theoretical setting of Bosonic Gaussian channels. As in the classical Kelly Criterion for optimal betting, we define the asymptotic doubling rate of the model and identify the optimal gambling strategy for fixed odds and probabilities of winning. The performance of the model are hence studied as a function of the input capital state under the assumption that the latter belongs to the set of Gaussian density matrices (i.e. displaced, squeezed thermal Gibbs states) revealing that the best option for the gambler is to devote all her/his initial resources into coherent state amplitude.

We develop a new market-making model, from the ground up, which is tailored towards high-frequency trading under a limit order book (LOB), based on the well-known classification of order types in market microstructure. Our flexible framework allows arbitrary order volume, price jump, and bid-ask spread distributions as well as the use of market orders. It also honors the consistency of price movements upon arrivals of different order types. For example, it is apparent that prices should never go down on buy market orders. In addition, it respects the price-time priority of LOB. In contrast to the approach of regular control on diffusion as in the classical Avellaneda and Stoikov [1] market-making framework, we exploit the techniques of optimal switching and impulse control on marked point processes, which have proven to be very effective in modeling the order-book features. The Hamilton-Jacobi-Bellman quasi-variational inequality (HJBQVI) associated with the control problem can be solved numerically via finite-difference method. We illustrate our optimal trading strategy with a full numerical analysis, calibrated to the order-book statistics of a popular Exchanged-Traded Fund (ETF). Our simulation shows that the profit of market-making can be severely overstated under LOBs with inconsistent price movements.

We introduce a method to predict which correlation matrix coefficients are likely to change their signs in the future in the high-dimensional regime, i.e. when the number of features is larger than the number of samples per feature. The stability of correlation signs, two-by-two relationships, is found to depend on three-by-three relationships inspired by Heider social cohesion theory in this regime. We apply our method to US and Hong Kong equities historical data to illustrate how the structure of correlation matrices influences the stability of the sign of its coefficients.

In this paper, Malliavin calculus is applied to arrive at exact formulas for the difference between the volatility swap strike and the zero vanna implied volatility for volatilities driven by fractional noise. To the best of our knowledge, our estimate is the rst to show the rigorous relationship between the zero vanna implied volatility and the volatility swap strike. In particular, we will see that the zero vanna implied volatility has a higher rate of convergence than the at-the-money (ATM) implied volatility for both zero and non-zero correlation and for all values of the Hurst parameter.

We generalize Quasi-Linear Means by restricting to the tail of the risk distribution and show that this can be a useful quantity in risk management since it comprises in its general form the Value at Risk, the Tail Value at Risk and the Entropic Risk Measure in a unified way. We then investigate the fundamental properties of the proposed measure and show its unique features and implications in the risk measurement process. Furthermore, we derive formulas for truncated elliptical models of losses and provide formulas for selected members of such models.

In this paper we consider an optimal investment and reinsurance problem with partially unknown model parameters which are allowed to be learned. The model includes multiple business lines and dependence between them. The aim is to maximize the expected exponential utility of terminal wealth which is shown to imply a robust approach. We can solve this problem using a generalized HJB equation where derivatives are replaced by generalized Clarke gradients. The optimal investment strategy can be determined explicitly and the optimal reinsurance strategy is given in terms of the solution of an equation. Since this equation is hard to solve, we derive bounds for the optimal reinsurance strategy via comparison arguments.

There are several researches that deal with the behavior of SEs and their relationships with different economical factors. These range from papers dealing with this subject through econometrical procedures to statistical methods known as copula. This article considers the impact of oil and gold price on Tehran Stock Exchange market (TSE). Oil and gold are two factors that are essential for the economy of Iran and their price are determined in the global market. The model used in this study is ARIMA-Copula. We used data from January 1998 to January 2011 as training data to find the appropriate model. The cross validation of model is measured by data from January 2011 to June 2011. We conclude that: (i) there is no significant direct relationship between gold price and the TSE index, but the TSE is indirectly influenced by gold price through other factors such as oil; and (ii) the TSE is not independent of the volatility in oil price and Clayton copula can describe such dependence structure between TSE and the oil price. Based on the property of Clayton copula, which has lower tail dependency, as the oil price drops, stock index falls. This means that decrease in oil price has an adverse effect on Iranian economy.

This paper uses stop-level passenger count data in four cities to understand the nation-wide bus ridership decline between 2012 and 2018. The local characteristics associated with ridership change are evaluated in Portland, Miami, Minneapolis/St-Paul, and Atlanta. Poisson models explain ridership as a cross-section and the change thereof as a panel. While controlling for change in frequency, jobs, and population, the correlation with local socio-demographic characteristics are investigated using data from the American Community Survey. The effect of changing neighborhood demographics on bus ridership are modeled using Longitudinal Employer-Household Dynamics data. At a point in time, neighborhoods with high proportions of non-white, carless, and most significantly, high-school-educated residents are the most likely to have high ridership. Over time, white neighborhoods are losing the most ridership across all four cities. Places with high concentrations of residents with college education and without access to a car also lose ridership at a faster rate in two of the cities. The sign and significance of these results remain consistent even when controlling for intra-urban migration. Although bus ridership is declining across neighborhood characteristics, these results suggest that the underlying cause must be primarily affecting the travel behavior of white bus riders. Shifts in neighborhood socio-demographics, however, were found to be modest and unlikely to be causing the nation-wide ridership crisis. Only in Miami is the proportion of white residents near the most frequent parts of the bus network increasing. There, demographic shifts may be contributing to the overall decline in bus ridership.