In this paper, we show how we can deploy machine learning techniques in the context of traditional quant problems. We illustrate that for many classical problems, we can arrive at speed-ups of several orders of magnitude by deploying machine learning techniques based on Gaussian process regression. The price we have to pay for this extra speed is some loss of accuracy. However, we show that this reduced accuracy is often well within reasonable limits and hence very acceptable from a practical point of view. The concrete examples concern fitting and estimation. In the fitting context, we fit sophisticated Greek profiles and summarize implied volatility surfaces. In the estimation context, we reduce computation times for the calculation of vanilla option values under advanced models, the pricing of American options and the pricing of exotic options under models beyond the Black–Scholes setting.
20 May 2021 in Journal of Sustainable Finance & Investment
In this paper, we examine the impact of including environmental, social and governance (ESG) criteria in the allocation of equity portfolios. We focus on the risk and return characteristics of the resulting ESG portfolios and investment strategies. Two specific measures are considered to quantify the ESG performance of a company; the ESG rating and the greenhouse gas (GHG) emission intensity. For both measures, we carry out empirical portfolio analyses with assets in either the STOXX Europe 600 or the Russell 1000 index. The ESG rating data analysis does not provide clear-cut evidence for enhanced performance of portfolios with either high or low ESG scores. We moreover illustrate that the choice of rating agency has an impact on the performance of ESG-constrained portfolios. The analysis on GHG intensities shows that portfolios with reduced emissions do not necessarily have increased risk or diminished returns.
It is already well documented that model risk is an important issue regarding the pricing of exotics (see Schoutens et al., in A perfect calibration! Now what?, Wilmott Magazine, March 2004: pp 66–78, 2004). Arguments have been made to put this into the perspective of bid-ask pricing using the theory of conic finance and pricing to acceptability (Cherny and Madan Review of Financial Studies, 22: 2571–2606, 2009). In this paper we show also the presence and importance of calibration risk. More particularly, we point out that a variety of plausible calibration methods lead again to serious price differences for exotics and different distributions of the P&L of the delta-hedging strategy. This is illustrated under the popular Heston stochastic volatility model, which is used among practitioners to price all kinds of exotic and structured products. This paper shows that it is prudent to take some additional safety margin into account for the pricing of these structured notes.
16 February 2011 in Mathematics and Financial Economics