The invention discloses a financial loan auditing method and
system based on a block chain and
machine learning, which are applied to a block
chain network and comprise super nodes and common nodes. The method comprises the following steps: when any node queries a request, counting the quantity of conflict information, and carrying out risk grading on loan users based on a static prediction resultand a
dynamic prediction result; and upgrading the common nodes which generate the static prediction result at the earliest and the
dynamic prediction result at the earliest into super nodes, and degrading the same number of super nodes into the common nodes according to a super node sorting
list and a sorting sequence. According to the invention, the defects of information islands of traditionalplatforms are overcome, user
blacklist sharing synchronization is realized, and joint auditing of users for loans is realized; through combined auditing of a static
risk model and a dynamic
risk model, the influence of subjective factors of manual auditing is avoided, and the accuracy and the growth of
risk identification are ensured; by adjusting the super nodes, the super nodes can be preventedfrom being rigidified and doing wrong jointly.