Learning minimum variance discrete hedging directly from the market

Option hedging is a critical risk management problem in finance. In the Black–Scholes model, it has been recognized that computing a hedging position from the sensitivity of the calibrated model option value function is inadequate in minimizing variance of the option hedge risk, as it fails to capture the model parameter dependence on the underlying price (see e.g. Coleman et al., J. Risk, 2001, 5(6), 63–89; Hull and White, J. Bank. Finance, 2017, 82, 180–190). In this paper, we demonstrate that this issue can exist generally when determining hedging position from the sensitivity of the option function, either calibrated from a parametric model from current option prices or estimated nonparametricaly from historical option prices. Consequently, the sensitivity of the estimated model option function typically does not minimize variance of the hedge risk, even instantaneously. We propose a data-driven approach to directly learn a hedging function from the market data by minimizing variance of the local hedge risk. Using the S&P 500 index daily option data for more than a decade ending in August 2015, we show that the proposed method outperforms the parametric minimum variance hedging method proposed in Hull and White [J. Bank. Finance, 2017, 82, 180–190], as well as minimum variance hedging corrective techniques based on stochastic volatility or local volatility models. Furthermore, we show that the proposed approach achieves significant gain over the implied BS delta hedging for weekly and monthly hedging.     

Forecasting U.S. money growth using economic uncertainty measures and regularisation techniques

This paper examines the out-of-sample forecasting properties of six different economic uncertainty variables for the growth of the real M2 and real M4 Divisia money series for the U.S. using monthly data. The core contention is that information on economic uncertainty improves the forecasting accuracy. We estimate vector autoregressive models using the iterated rolling-window forecasting scheme, in combination with modern regularisation techniques from the field of machine learning. Applying the Hansen-Lunde-Nason model confidence set approach under two different loss functions reveals strong evidence that uncertainty variables that are related to financial markets, the state of the macroeconomy or economic policy provide additional informational content when forecasting monetary dynamics. The use of regularisation techniques improves the forecast accuracy substantially.     

Systemic event prediction by an aggregate early warning system: An application to the Czech Republic

This work develops an early warning framework for assessing systemic risks and predicting systemic events over a short horizon of six quarters and a long horizon of 12 quarters on a panel of 14 countries, both advanced and developing. First, we build a financial stress index to identify the starting dates of systemic financial crises for each country in the panel. Second, early warning indicators for the assessment and prediction of systemic risk are selected in a two-step approach; we find relevant prediction horizons for each indicator by a univariate logit model followed by the application of Bayesian model averaging to identify the most useful indicators. Finally, we observe the performance of the constructed EWS over both horizons on the Czech data and find that the model over the long horizon outperforms the EWS over the short horizon. For both horizons, out-of-sample probability estimates do not deviate substantially from their in-sample estimates, indicating a good out-of-sample performance for the Czech Republic.     

An explainable machine learning approach to improve take-off time predictions

Accurate aircraft trajectory predictions are necessary to compute exact traffic demand figures, which are crucial for an efficient and effective air traffic flow and capacity management. At present, the uncertainty of the take-off time is one of the major contributions to the loss of trajectory predictability. In the EUROCONTROL Maastricht Upper Area Control Centre, the predicted take-off time for each individual flight relies on the information received from the Enhanced Traffic Flow Management System. However, aircraft do not always take-off at the times reported by this system due to several factors, which effects and interactions are too complex to be expressed with hard-coded rules. Previous work proposed a machine learning model that, based on historical data, was able to predict the take-off time of individual flights from a set of input features that effectively captures some of these elements. The model demonstrated to reduce by 30% the take-off time prediction errors of the current system one hour before the time that flight is scheduled to depart from the parking position. This paper presents an extension of the model, which overcomes this look-ahead time constraint and allows to improve take-off time predictions as early as the initial flight plan is received. In addition, a subset of the original set of input features has been meticulously selected to facilitate the implementation of the solution in an operational air traffic flow and capacity management system, while minimising the loss of predictive power. Finally, the importance and interactions of the input features are thoroughly analysed with additive feature attribution methods.     

Overcoming localization of knowledge — the role of professional service firms

The literature on organizational learning asserts that external learning is often limited geographically and technologically. We scrutinize to what extent organizations acquire external knowledge by accessing external knowledge repositories. We argue that professional service firms (PSFs) grant access to nonlocalized knowledge repositories and thereby not only facilitate external learning but also help to overcome localization. Focusing on patent law firms, we test our predictions using a unique dataset of 544,820 pairs of European patent applications. Analyzing patterns of knowledge flows captured in patent citations, we find that accessing a PSF's repository facilitates the acquisition of external knowledge. As the effect is more pronounced for knowledge that is distant to a focal organization, we conclude that having access to a knowledge repository compensates for localization disadvantages. Copyright © 2013 John Wiley & Sons, Ltd.     

Creating financial statements using FRx within Microsoft Dynamics GP: Learning vs. teaching

This project requires you to create financial statements using FRx within Microsoft Dynamics GP, an enterprise system. The project emphasizes the learner-centered paradigm rather than a teacher-centered educational paradigm. Researchers have found great importance in the learner-centered approach in educating students, especially in information systems (Landry, Saulnier, Wagner, & Longenecker, 2008; Saulnier, Landry, & Wagner, 2008). Major differences exist between the two approaches; for example, the professor gives information and evaluates, and emphasizes the right answer in a teacher-centered approach. The professor coaches and facilitates, and emphasizes that students generate good questions and learn from mistakes in a learner-centered approach. This project utilizes the learner-centered approach, an effective approach for you to use in today’s environment.     

Adaptive learning and distributional dynamics in an incomplete markets model

Recent research shows that several DSGE models provide a closer fit to the data under adaptive learning. This paper extends this research by introducing adaptive learning in the model of Krusell and Smith (1998) with uninsurable idiosyncratic risks and aggregate uncertainty. A first contribution of this paper establishes that the equilibrium of this framework is stable under least-squares learning. The second contribution consists of showing that bounded rationality enhances the ability of this model to match the distribution of income in the US. Learning increases significantly the Gini coefficients because of the opposite effects on consumption of the capital-rich and of the capital-poor agent. The third contribution is an empirical exercise that shows that learning can account for increases in the income Gini coefficient of up to 25% in a period of 28 years. Overall, these findings suggest that adaptive learning has important distributional repercussions in this class of models.     

Learning to bid in sequential Dutch auctions

We propose an agent-based computational model to investigate sequential Dutch auctions with particular emphasis on markets for perishable goods and we take as an example wholesale fish markets. Buyers in these markets sell the fish they purchase on a retail market. The paper provides an original model of boundedly rational behavior for wholesale buyers׳ behavior incorporating learning to improve profits, conjectures as to the bids that will be made and fictitious learning. We analyze the dynamics of the aggregate price under different market conditions in order to explain the emergence of market price patterns such as the well-known declining price paradox and the empirically observed fact that the very last transactions in the day may be at a higher price. The proposed behavioral model provides alternative explanations for market price dynamics to those which depend on standard hypotheses such as diminishing marginal profits. Furthermore, agents learn the option value of having the possibility of bidding in later rounds. When confronted with random buyers, such as occasional participants or new entrants, they learn to bid in the optimal way without being conscious of the strategies of the other buyers. When faced with other buyers who are also learning their behavior still displays some of the characteristics learned in the simpler case even though the problem is not analytically tractable.     

Forecasting China's foreign exchange reserves using dynamic model averaging: The roles of macroeconomic fundamentals,financial stress and economic uncertainty

We develop models for examining possible predictors of growth of China's foreign exchange reserves that embrace Chinese and global trade, financial and risk (uncertainty) factors. Specifically, by comparing with other alternative models, we show that the dynamic model averaging (DMA) and dynamic model selection (DMS) models outperform not only linear models (such as random walk, recursive OLS-AR(1) models, recursive OLS with all predictive variables models) but also the Bayesian model averaging (BMA) model for examining possible predictors of growth of those reserves. The DMS is the best overall across all forecast horizons. While some predictors matter more than others over the forecast horizons, there are few that stand the test of time. The US–China interest rate differential has a superior predictive power among the 13 predictors considered, followed by the nominal effective exchange rate and the interest rate spread for most of the forecast horizons. The relative predictive prowess of the oil and copper prices alternates, depending on the commodity cycles. Policy implications are also provided.     

Learning,large deviations and rare events

We examine the role of generalized stochastic gradient constant gain (SGCG) learning in generating large deviations of an endogenous variable from its rational expectations value. We show analytically that these large deviations can occur with a frequency associated with a fat-tailed distribution even though the model is driven by thin-tailed exogenous stochastic processes. We characterize these large deviations, driven by sequences of consistently low or consistently high shocks and then apply our model to the canonical asset pricing framework. We demonstrate that the tails of the stationary distribution of the price–dividend ratio will follow a power law.