Hepatitis C virus (HCV) is a major public health concern, with over 70 million people infected worldwide, who are at risk for developing life-threatening liver disease. No vaccine is available, and immunity against the virus is not well understood. Following the acute stage, HCV usually causes chronic infections. However, approximately 30% of infected individuals spontaneously clear the virus. Therefore, using HCV as a model for comparing immune responses between spontaneous clearer (SC) and chronically infected (CI) individuals may empower the identification of mechanisms governing viral infection outcomes. We demonstrate the first in-depth analysis of adaptive immune receptor repertoires in individuals with current or past HCV infection. SC individuals, in contrast to CI patients, develop a cluster of antibodies with distinct properties. These antibodies’ characteristics were used in a machine learning framework to accurately predict infection outcome. By integrating these data with combinatorial antibody phage display library technology, we constructed two antibodies characterized by high neutralization breadth, which are associated with clearance. In addition, we revealed distinct epitopes that are associated with infection outcome by using sera obtained from SC or CI individuals and identifying epitopes bound to these sera from a random peptides phage display library. This study provides insight into the nature of effective immune response against HCV and demonstrates an innovative approach for constructing antibodies correlating with successful infection clearance. It may have clinical implications for prognosis of the future status of infection, and the design of effective immunotherapies and a vaccine for HCV.