We present a number of related comparison results, which allow to compare moment explosion times, moment generating functions and critical moments between rough and non-rough Heston models of stochastic volatility. All results are based on a comparison principle for certain non-linear Volterra integral equations. Our upper bound for the moment explosion time is different from the bound introduced by Gerhold, Gerstenecker and Pinter (2018) and tighter for typical parameter values. The results can be directly transferred to a comparison principle for the asymptotic slope of implied volatility between rough and non-rough Heston models. This principle shows that the ratio of implied volatility slopes in the rough vs. the non-rough Heston model increases at least with power-law behavior for small maturities.

Antibiotic resistance constitutes a major health threat. Predicting bacterial causes of infections is key to reducing antibiotic misuse, a leading driver of antibiotic resistance. We train a machine learning algorithm on administrative and microbiological laboratory data from Denmark to predict diagnostic test outcomes for urinary tract infections. Based on predictions, we develop policies to improve prescribing in primary care, highlighting the relevance of physician expertise and policy implementation when patient distributions vary over time. The proposed policies delay antibiotic prescriptions for some patients until test results are known and give them instantly to others. We find that machine learning can reduce antibiotic use by 7.42 percent without reducing the number of treated bacterial infections. As Denmark is one of the most conservative countries in terms of antibiotic use, this result is likely to be a lower bound of what can be achieved elsewhere.

Prediction problems in finance go beyond estimating the unknown parameters of a model (e.g of expected returns). This is because such a model would have to include knowledge about the market participants' propensity to change their opinions on the validity of that model. This leads to a circular situation characteristic of markets, where participants collectively create the target variables they wish to estimate. In this paper, we introduce a framework for generating expectation models and study the conditions under which they are adopted by a majority of market participants.

An increasing concern in power systems is on how to elicit flexibilities in demands for better supply/demand balance. To this end, several differentiated energy services have been put forward, wherein demands are discriminated by their different flexibility levels. Motivated by the duration-differentiated energy services, we have proposed energy services differentiated by durations, arrival times, and deadlines. The purpose of this paper is to study the market implementation of such multiple-arrival multiple-deadline differentiated energy services. To verify the economic feasibility, we establish that in a forward market, there exists an efficient competitive equilibrium which attains the maximum social welfare. In addition, we show that future information will influence current decisions on power delivery by studying a special kind of causal allocation policy. Finally, we propose two tractable integer programs, namely the optimal arbitrage and the minimum-cost allocation problems, which can be embedded in a two-level hierarchical real-time implementation of differentiated energy services.

Monte Carlo methods are core to many routines in quantitative finance such as derivatives pricing, hedging and risk metrics. Unfortunately, Monte Carlo methods are very computationally expensive when it comes to running simulations in high-dimensional state spaces where they are still a method of choice in the financial industry. Recently, Tensor Processing Units (TPUs) have provided considerable speedups and decreased the cost of running Stochastic Gradient Descent (SGD) in Deep Learning. After having highlighted computational similarities between training neural networks with SGD and stochastic process simulation, we ask in the present paper whether TPUs are accurate, fast and simple enough to use for financial Monte Carlo. Through a theoretical reminder of the key properties of such methods and thorough empirical experiments we examine the fitness of TPUs for option pricing, hedging and risk metrics computation. We show in the following that Tensor Processing Units (TPUs) in the cloud help accelerate Monte Carlo routines compared to Graphics Processing Units (GPUs) which in turn decreases the cost associated with running such simulations while leveraging the flexibility of the cloud. In particular we demonstrate that, in spite of the use of mixed precision, TPUs still provide accurate estimators which are fast to compute. We also show that the Tensorflow programming model for TPUs is elegant, expressive and simplifies automated differentiation.

We address the issue of the factors driving startup success in raising funds. Using the popular and public startup database Crunchbase, we explicitly take into account two extrinsic characteristics of startups: the competition that the companies face, using similarity measures derived from the Word2Vec algorithm, as well as the position of investors in the investment network, pioneering the use of Graph Neural Networks (GNN), a recent deep learning technique that enables the handling of graphs as such and as a whole. We show that the different stages of fundraising, early- and growth-stage, are associated with different success factors. Our results suggest a marked relevance of startup competition for early stage while growth-stage fundraising is influenced by network features. Both of these factors tend to average out in global models, which could lead to the false impression that startup success in fundraising would mostly if not only be influenced by its intrinsic characteristics, notably those of their founders.

Training deep learning models that generalize well to live deployment is a challenging problem in the financial markets. The challenge arises because of high dimensionality, limited observations, changing data distributions, and a low signal-to-noise ratio. High dimensionality can be dealt with using robust feature selection or dimensionality reduction, but limited observations often result in a model that overfits due to the large parameter space of most deep neural networks. We propose a generative model for financial time series, which allows us to train deep learning models on millions of simulated paths. We show that our generative model is able to create realistic paths that embed the underlying structure of the markets in a way stochastic processes cannot.

With the rise of the electronic trading, corporate bond traders have access to data information of past trades. As a first step to automation, they have to start monitoring their own trades, and using past data to build a benchmark for the expected transaction costs with given bond characteristics and market conditions. Given the limited liquidity of corporate bonds which are traded few times daily, a statistical model is the only way to benchmark effective costs. It brings focused attention of the dealing desk of an institutional investor on the most costly trades, and enables identifying and improving business practices such as the market timing for selection counterparties.

Unlike existing literature which focuses on general measurements using OLS, this paper takes the viewpoint of a given investor, and provides an analytical approach to establish a benchmark for transaction cost analysis in corporate bond tradings. Regularized methods are used to improve the selection of explanatory variables, as fewer variables provide easier analytics from a business perspective. This benchmark is constructed in two steps. The first step is the regression analysis with cross validation to identify abnormal trades. Three regression approaches, OLS, two-step Lasso and Elastic Net, are adopted to identify key features for the bid-ask spread of corporate bonds. The second step is to use the non-parametric approach to estimate the amplitude and decay pattern of price impact. A key discovery is the price impact asymmetry between customer-buy orders and consumer-sell orders. This benchmark can aid decision makings for retail investors when requesting quotes on the electronic platform.