In this thesis, the pricing of counterparty credit risk on an OTC plain vanilla interest rate swap is investigated. Counterparty credit risk can be defined as the risk that a counterparty in a financial contract might not be able or willing to fulfil their obligations. This risk has to be taken into account in the valuation of an OTC derivative. The market price of the counterparty credit risk is known as the Credit Value Adjustment (CVA). In a bilateral contract, such as a swap, the party’s own creditworthiness also has to be taken into account, leading to another adjustment known as the Debit Value Adjustment (DVA). Since 2013, the international accounting standards (IFRS) states that these adjustments have to be done in order to reflect the fair value of an OTC derivative. A short background and the derivation of CVA and DVA is presented, including related topics like various risk mitigation techniques, hedging of CVA, regulations etc.. Four different pricing frameworks are compared, two more sophisticated frameworks and two approximative approaches. The most complex framework includes an interest rate model in form of the LIBOR Market Model and a credit model in form of the Cox-Ingersoll- Ross model. In this framework, the impact of dependencies between credit and market risk factors (leading to wrong-way/right-way risk) and the dependence between the default time of different parties are investigated. / I den här uppsatsen har prissättning av motpartsrisk för en OTC ränteswap undersökts. Motpartsrisk kan definieras som risken att en motpart i ett finansiellt kontrakt inte har möjlighet eller viljan att fullfölja sin del av kontraktet. Motpartsrisken måste tas med I värderingen av ett OTC-derivat. Marknadspriset på motpartrisken är känt som Credit Value Adjustment (CVA). I ett bilateralt kontrakt, t.ex. som en swap, måste även den egna kreditvärdighet tas med i värderingen, vilket leder till en justering som är känd som Debit Value Adjustment (DVA). Sedan 2013 skall, enligt den internationella redovisningsstandarden (IFRS), dessa prisjusteringar göras vid redovisningen av värdet för ett OTC derivat. En kort bakgrund samt härledningen av CVA och DVA ar presenterade tillsammans med relaterade ämnen. Fyra olika metoder för att beräkna CVA har jämförts, två mer sofistikerade metoder och två approximativa metoder. I den mest avancerade metoden används en räntemodell i form av LIBOR Market Model samt en kreditmodell i form av en Cox-Ingersoll-Ross modell. I den här metoden undersöks även påverkan av CVA då det existerar beroenden mellan marknads

Counterparty risk calculations have gained importance after the latest financial crisis. The bankruptcy of Lehman Brothers showed that even large financial institutiones face a risk of default. Hence, it is important to measure the risk of default for all the contracts written between financial institutions. Credit Value Adjustment, CVA, is an industry standard method for such calculations. Nevertheless, the implementation of this method is contract dependent and the necessary computer simulations can be very intensive. Monte Carlo simulations have for a long time been known as a precise but slow technique to evaluate the cash flows for contracts of all kinds. Measuring the exposure of a contract written on structured products might require half a day of calculations if the implementation is written without significant optimization. Several ideas have been presented by researchers and applied in the industry, the idea explored and implemented in this thesis was based on using Artificial Neural Networks in Python. This procedure require a decomposition of the Expected Exposure calculation within the CVA and generating a large data set using a standard Monte Carlo simulation. Three network architectures have been tested and the final performance was compared with using standard techniques for the very same calculation. The performance gain was significant, a portfolio of 100 counterparties with 10 contracts each would take 20 minutes of calculations in total when using the best performing architecture whereas a parallel C++ implementation of the standard method would require 2.6 days.