Operations include generating proposals for accounts payable and accounts receivable netting across multiple trading partners. A netting proposal system uses a machine learning model to generate netting proposals that are likely to be approved by the respective trading partners. The netting proposal system identifies characteristics of attributes of previously accepted netting proposals. Candidate attributes, with the same characteristics of attributes of previously accepted netting proposals, are selected for a new netting proposal. The netting proposal system further identifies characteristics of attributes of previously rejected netting proposals. Candidate attributes, without the same characteristics of attributes of previously rejected netting proposals, are selected for the new netting proposal. Furthermore, candidate attributes, with the same characteristics of attributes of previously rejected netting proposals, are not selected for the new netting proposal.