| CPC G06Q 20/42 (2013.01) [G06N 20/20 (2019.01)] | 20 Claims |

|
1. A computer-implemented method for reducing false positives and recommending chargeback representment, comprising:
receiving, by one or more processors, data associated with at least one disputed transaction for at least one user, wherein the received data includes user-specific information, merchant-specific information, or a combination thereof;
uploading, by the one or more processors via a set of stored executable data, import instructions in a form of one or more import scripts, the received data to an input log database;
inputting, by the one or more processors, the received data uploaded to the input log database in a plurality of machine learning models configured to calculate a corresponding probability of success in a chargeback representment for the at least one disputed transaction, wherein each of the plurality of machine learning models is assigned a weight based on a training and re-training process to reduce false positives;
in response to the inputting, receiving, by the one or more processors, a plurality of probabilities corresponding to the plurality of machine learning models;
determining, by the one or more processors, a majority decision from the plurality of probabilities from the plurality of machine learning models;
determining, by the one or more processors, a prediction based, at least in part, on the majority decision;
generating, by the one or more processors, a presentation of at least one recommendation on the chargeback representment based, at least in part, on the prediction in a user interface of at least one device associated with the at least one user;
re-training, by the one or more processors, at least one of the plurality of machine learning models based on the recommendation on the chargeback representment and the corresponding probability of success in a chargeback representment for the at least one disputed transaction; and
assigning, by the one or more processors, an updated assigned weight for each of the plurality of machine learning models based on the re-training of at least one of the plurality of machine learning models, wherein the updated assigned weight reduces false positives.
|