Dengue infection is a global threat. High-throughput sequencing enables the identification of the multitude of antibodies elicited in response to dengue infection. We have applied different machine learning methods to the large-scale antibody repertoire sequence data. Our results determine best performing algorithms for the detection and prediction of antibody patterns at the repertoire and antibody sequence levels in dengue infected individuals based on the benchmarking existing and novel encoding techniques, and after investigating the parameter space of various models. Our results support antibody discovery and vaccine design in dengue.