We propose a fully data-driven approach to calibrate local stochastic volatility (LSV) models, circumventing in particular the ad hoc interpolation of the volatility surface. To achieve this, we parametrize the leverage function by a family of feed-forward neural networks and learn their parameters directly from the available market option prices. This should be seen in the context of neural SDEs and (causal) generative adversarial networks: we generate volatility surfaces by specific neural SDEs, whose quality is assessed by quantifying, possibly in an adversarial manner, distances to market prices. The minimization of the calibration functional relies strongly on a variance reduction technique based on hedging and deep hedging, which is interesting in its own right: it allows the calculation of model prices and model implied volatilities in an accurate way using only small sets of sample paths. For numerical illustration we implement a SABR-type LSV model and conduct a thorough statistical performance analysis on many samples of implied volatility smiles, showing the accuracy and stability of the method.

By significant improvements in modern electrical systems, planning for unit commitment and power dispatching of them are two big concerns between the researchers. Short-term load forecasting plays a significant role in planning and dispatching them. In recent years, numerous works have been done on Short-term load forecasting. Having an accurate model for predicting the load can be beneficial for optimizing the electrical sources and protecting energy. Several models such as Artificial Intelligence and Statistics model have been used to improve the accuracy of load forecasting. Among the statistics models, time series models show a great performance. In this paper, an Autoregressive integrated moving average (SARIMA) - generalized autoregressive conditional heteroskedasticity (GARCH) model as a powerful tool for modeling the conditional mean and volatility of time series with the T-student Distribution is used to forecast electric load in short period of time. The attained model is compared with the ARIMA model with Normal Distribution. Finally, the effectiveness of the proposed approach is validated by applying real electric load data from the Electric Reliability Council of Texas (ERCOT). KEYWORDS: Electricity load, Forecasting, Econometrics Time Series Forecasting, SARIMA

The pricing of currency options is largely dependent on the dynamic relationship between a pair of currencies. Typically, the pricing of options with payoffs dependent on multi-assets becomes tricky for reasons such as the non-Gaussian distribution of financial variable and non-linear macroeconomic relations between these markets. We study the options based on the currency pair US dollar and Indian rupee (USD-INR) and test several pricing formulas to evaluate the performance under different volatility regimes. We show the performance of the variance gamma and the symmetric variance gamma models during different volatility periods as well as for different moneyness, in comparison to the modified Black-Scholes model. In all cases, variance gamma model outperforms Black-Scholes. This can be attributed to the control of kurtosis and skewness of the distribution that is possible using the variance gamma model. Our findings support the superiority of variance gamma process of currency option pricing in better risk management strategies.

Rational respondents to economic surveys may report as a point forecast any measure of the central tendency of their (possibly latent) predictive distribution, for example the mean, median, mode, or any convex combination thereof. We propose tests of forecast rationality when the measure of central tendency used by the respondent is unknown. We overcome an identification problem that arises when the measures of central tendency are equal or in a local neighborhood of each other, as is the case for (exactly or nearly) symmetric distributions. As a building block, we also present novel tests for the rationality of mode forecasts. We apply our tests to survey forecasts of individual income, Greenbook forecasts of U.S. GDP, and random walk forecasts for exchange rates. We find that the Greenbook and random walk forecasts are best rationalized as mean, or near-mean forecasts, while the income survey forecasts are best rationalized as mode forecasts.

Can an asset manager plan the optimal timing for her/his hedging strategies given market conditions? The standard approach based on Markowitz or other more or less sophisticated financial rules aims to find the best portfolio allocation thanks to forecasted expected returns and risk but fails to fully relate market conditions to hedging strategies decision. In contrast, Deep Reinforcement Learning (DRL) can tackle this challenge by creating a dynamic dependency between market information and hedging strategies allocation decisions. In this paper, we present a realistic and augmented DRL framework that: (i) uses additional contextual information to decide an action, (ii) has a one period lag between observations and actions to account for one day lag turnover of common asset managers to rebalance their hedge, (iii) is fully tested in terms of stability and robustness thanks to a repetitive train test method called anchored walk forward training, similar in spirit to k fold cross validation for time series and (iv) allows managing leverage of our hedging strategy. Our experiment for an augmented asset manager interested in sizing and timing his hedges shows that our approach achieves superior returns and lower risk.

On April 16th, The White House launched "Opening up America Again" (OuAA) campaign while many U.S. counties had stay-at-home orders in place. We created a panel data set of 1,563 U.S. counties to study the impact of U.S. counties' stay-at-home orders on community mobility before and after The White House's campaign to reopen the country. Our results suggest that before the OuAA campaign stay-at-home orders were effective in decreasing time spent at retail & recreation places and in increasing time spent at home. These stay-at-home orders were less effective in more conservative counties. We further find that the OuAA campaign significantly increased time spent at retail & recreation places and decreased time spent at home particularly in conservative counties. However, in conservative counties with stay-at-home orders in place, OuAA campaign was less effective when compared to conservative counties without stay-at-home orders. These findings signal promising news for local (county and state) authorities. That is, even when the federal government is reopening the country, the local authorities that enforced stay-at-home restrictions were to some extent effective.