# Derivatives pricing

##### An ‘optimal’ way to calculate future P&L distributions?

Quants use neural networks to upgrade classic options pricing model

##### Axes that matter: PCA with a difference

Differential PCA is introduced to reduce the dimensionality in derivative pricing problems

##### Derivatives pricing starts feeling the heat of climate change

Quants find physical and transition risks can lead to significant rise in CVA

##### Show your workings: lenders push to demystify AI models

Machine learning could help with loan decisions – but only if banks can explain how it works. And that’s not easy

##### Capturing the effects of climate change on CVA and FVA

A framework to incorporate climate change risk into derivative prices is presented

##### How XVA quants learned to trust the machine

Initial scepticism about using neural networks for derivatives pricing is giving way to enthusiasm

##### Deep XVAs and the promise of super-fast pricing

Intelligent robots can value complex derivatives in minutes rather than hours

##### Hedging valuation adjustment gets cold shoulder from banks

Dealers back the idea of charging for hedging costs but not as part of a new XVA

##### Podcast: Piterbarg on medians and machine learning

How the Libor transition inspired NatWest quant’s latest paper on exotic derivatives valuation

##### The arcsine law for quantile derivatives

A new pricing model for quantile-based derivatives, such as Napoleon options, is presented

##### Dealers applaud proposal to halt yen Libor swaps after Q3

BoJ working group timetable viewed as likely to boost liquidity in nascent Tonar market

##### The cost of hedging XVA

HVA is framed consistently with other valuation adjustments

##### Gradient boosting for quantitative finance

In this paper, the authors discuss how tree-based machine learning techniques can be used in the context of derivatives pricing.

##### Hedging valuation adjustment: fact and friction

Transaction costs’ impact on hedging can now be quantified

##### Deep asymptotics

Introducing a new technique to control the behaviour of neural networks

##### Goldman, IBM lay out quantum road map for derivatives pricing

Researchers estimate 7,500 logical qubits and 46 million T-gates would be needed to price options

##### A step closer to the perfect volatility model

Research on ‘rough volatility’ gives fresh insight into financial fluctuations, quant expert explains

##### Finite difference schemes with exact recovery of vanilla option prices

A model unifies the classic local vol and binomial trees to accurately price options

##### TSE outage throws structured notes into tailspin

Trading shutdown on October 1 disrupted observation dates for some structured products

##### Differential machine learning: the shape of things to come

A derivative pricing approximation method using neural networks and AAD speeds up calculations

##### A positive response to negative oil prices

Overhauling pricing models could reap rewards even if prices don’t cross zero again

##### A tale of two (or three, or four) models

Performance measure based on quality of replicating portfolios outperforms ‘P&L explain’, new paper claims

##### Second-order Monte Carlo sensitivities

This paper considers the problem of efficiently computing the full matrix of second-order sensitivities of a Monte Carlo price when the number of inputs is large.

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.