tMissing data in large insurance datasets affects the learning and classification accuracies in predictivemodelling. Insurance datasets will continue to increase in size as more variables are added to aid inmanaging client risk and will therefore be even more vulnerable to missing data. This paper proposes ahybrid multi-layered artificial immune system and genetic algorithm for partial imputation of missingdata in datasets with numerous variables. The multi-layered artificial immune system creates and storesantibodies that bind to and annihilate an antigen. The genetic algorithm optimises the learning processof a stimulated antibody. The uation of the imputation is performed using the RIPPER, k-nearestneighbour-tMissing data in large insurance datasets affects the learning and classification accuracies in predictivemodelling. Insurance datasets will continue to increase in size as more variables are added to aid inmanaging client risk and will therefore be even more vulnerable to missing data. This paper proposes ahybrid multi-layered artificial immune system and genetic algorithm for partial imputation of missingdata in datasets with numerous variables. The multi-layered artificial immune system creates and storesantibodies that bind to and annihilate an antigen. The genetic algorithm optimises the learning processof a stimulated antibody. The　uation of the imputation is performed using the RIPPER, k-nearestneighbour