System and method for facilitating model-based classification of transactions

A method of facilitating model-based dividend classification of transactions, the method being implemented by a computer system comprising one or more processors executing computer program instructions that, when executed, perform the method, the method comprising:

• obtaining resolved exceptions information regarding resolved exceptions, the resolved exceptions information indicating the resolved exceptions and, for each resolved exception of the resolved exceptions, a set of attributes of a transaction for which the resolved exception was triggered;
• providing, as input to a prediction model, the resolved exceptions information to obtain multiple decision trees via the prediction model,
• each decision tree of the multiple decision trees comprising nodes and conditional branches, each node of the nodes of the decision tree indicating a probability of a dividend-related classification for a transaction that corresponds to the node;
• wherein the neural network comprises multiple layers of neural units, and wherein a signal path traverses from front layers to back layers of the multiple layers, to obtain each decision tree;
• obtaining a first decision tree from the multiple decision trees obtained via the prediction model;
• processing, based on the first decision tree, unresolved exception information regarding unresolved exceptions to determine which of the first decision tree's nodes respectively correspond to transactions for which the unresolved exceptions were triggered;
• and
• assigning dividend-related classifications to the transactions based on which of the first decision tree's nodes respectively correspond to the transactions, a first transaction being assigned a first dividend-related classification based on the first transaction being determined to correspond to a first node.

A system for facilitating model-based dividend classification of transactions, the system comprising:

• a computer system that comprises one or more processors programmed with computer program instructions that, when executed, cause the computer system to:
• obtain resolved exceptions information regarding resolved exceptions, the resolved exceptions information indicating the resolved exceptions and, for each resolved exception of the resolved exceptions, a set of attributes of a transaction for which the resolved exception was triggered;
• provide, as input to a prediction model, the resolved exceptions information to obtain multiple decision trees via the prediction model,
• each decision tree of the multiple decision trees comprising nodes and conditional branches, each node of the nodes of the decision tree indicating a probability of a dividend-related classification for a transaction that corresponds to the node;
• wherein the neural network comprises multiple layers of neural units, and wherein a signal path traverses from front layers to back layers of the multiple layers, to obtain each decision tree;
• obtain a first decision tree from the multiple decision trees obtained via the prediction model;
• process, based on the first decision tree, unresolved exception information regarding unresolved exceptions to determine which of the first decision tree's nodes respectively correspond to transactions for which the unresolved exceptions were triggered;
• and
• assign dividend-related classifications to the transactions based on which of the first decision tree's nodes respectively correspond to the transactions, a first transaction being assigned a first dividend-related classification based on the first transaction being determined to correspond to a first node.