Negative selection is an immune-inspired algorithm which is typically applied to anomaly detection problems. We present an empirical investigation of the generalization capability of the Hamming negative selection, when combined with the r-chunk affinity metric. Our investigations reveal that when using the r-chunk metric, the length
is a crucial parameter and is inextricably linked to the input data being analyzed. Moreover, we propose that input data with different characteristics, i.e. different positional biases, can result in an incorrect generalization effect.