EVENT PREDICTION USING CLASSIFIER AS COARSE FILTER

    公开(公告)号:US20220309573A1

    公开(公告)日:2022-09-29

    申请号:US17842321

    申请日:2022-06-16

    Abstract: In an aspect, the present application describes a method including: obtaining account data associated with an account; passing at least some of the account data through a non-sufficient funds classifier, the non-sufficient funds classifier being a machine learning classifier configured to classify the account as either likely to have a non-sufficient funds event or unlikely to have a non-sufficient funds event, the machine learning classifier configured to evaluate a plurality of parameters associated with the account data; in response to determining that the account is likely to have a non-sufficient funds event, forecasting a balance for the account, wherein forecasting the balance for the account includes; and providing, to a client device associated with the account, a notification based on a forecasted balance.

    IDENTIFYING RECURRENT TRANSFER PATTERNS FOR AN ACCOUNT FROM PATTERNS FOR OTHER ACCOUNTS

    公开(公告)号:US20210103980A1

    公开(公告)日:2021-04-08

    申请号:US16592985

    申请日:2019-10-04

    Abstract: In an aspect, the present application describes a method including: identifying, from a set of accounts each having a transfer listing that includes a plurality of transfers with a first counterparty, a first rule; identifying, for a first account not included in the set of accounts, an initial transfer with the first counterparty; identifying one or more projected future transfers for first account based on a date associated with the initial transfer and the first rule; detecting one or more further transfers with the first counterparty from the transfer listing for the first account; determining, based on the one or more further transfers and the initial transfer, that a second rule matches a pattern defined by the further transfers and the initial transfers better than the first rule; and providing a notification to a client device associated with the first account based on the second rule.

    EVENT PREDICTION USING CLASSIFIER AS COARSE FILTER

    公开(公告)号:US20210103979A1

    公开(公告)日:2021-04-08

    申请号:US16592966

    申请日:2019-10-04

    Abstract: In an aspect, the present application describes a method including: obtaining account data associated with an account; passing at least some of the account data through a non-sufficient funds classifier, the non-sufficient funds classifier being a machine learning classifier configured to classify the account as either likely to have a non-sufficient funds event or unlikely to have a non-sufficient funds event, the machine learning classifier configured to evaluate a plurality of parameters associated with the account data; in response to determining that the account is likely to have a non-sufficient funds event, forecasting a balance for the account, wherein forecasting the balance for the account includes; and providing, to a client device associated with the account, a notification based on a forecasted balance.

    SYSTEMS AND METHODS FOR IDENTIFYING RECURRENT TRANSFER PATTERNS

    公开(公告)号:US20210103908A1

    公开(公告)日:2021-04-08

    申请号:US16592894

    申请日:2019-10-04

    Abstract: In an aspect, the present application describes a computer-implemented method including: storing a set of candidate rules, the set of candidate rules defining payment cycles; identifying, from a transaction history for an account, an actual set of transfers made to a first recipient; identifying a first reference transfer from the actual set of transfers; for each of at least a plurality of candidate rules in the set of candidate rules, identifying, based on the first reference transfer, an expected set of transfers for that candidate rule; identifying one of the candidate rules as a closest rule for the actual set of transfers; identifying a future expected transfer based on the identified one of the candidate rules; and providing a notification to a client device associated with the account of the future expected transfer.

Patent Agency Ranking