Estimation of early termination of financial derivatives

Sammanfattning: In terms of pricing financial derivatives, contractual length plays a important role in pricing risk. A contract with long duration will have more associated risk in comparison with a contract with low duration, everything else equal. In this thesis work we examine whether information about the derivative contract and involved parties (the counterparty) could be used in a model to accurately predict both probability and time if the contract would terminate earlier than the predetermined contractual length. By modelling the termination time with deep neural networks and assuming the probability distribution of termination time directly, we find that it is possible to predict when early termination of derivative contracts would occur significantly more accurate than assuming that contracts will always live to their original maturity date.