Abstract: Techniques are disclosed relating to transaction classification. In some embodiments, a computer system trains an initial transaction classifier based on pre-transaction data and post-transaction data for a first set of transactions for which training labels have been generated. The computer system may input, to the trained initial transaction classifier, pre-transaction data and post-transaction data for a second set of transactions for which training labels have not been generated. The trained initial transaction classifier may generate classifier outputs based on the input. The computer system may select a subset of the second set of transactions whose classifier outputs meet a confidence threshold and may generate training labels for transactions in the selected subset based on their classifier outputs.