International Business Machines Corporation

Visa International Service Association

Yinle Zhou

Scott Schumacher

Alan Xia

Michael Poplavski

Prachi Snehal

Sean J Welleck

Suman Mukherjee

Anup Tripathi

Karl J Weinmeister

Robert David Pritchard, Jr

A computer-implemented method for automated forecasting of cash flow includes: monitoring, while a plurality of first transactions are being processed in a payment network, payable transaction data associated with the plurality of first transactions, the plurality of first transactions initiated with at least one account issued to a merchant; monitoring, while a plurality of second transactions are being processed in a payment network, receivable transaction data associated with the plurality of second transactions, the plurality of second transactions between the merchant and a plurality of users; determining, based on the payable transaction data and the receivable transaction data, a plurality of seasonal variables; and generating a cash flow forecast associated with the merchant, the cash flow forecast generated based on the plurality of seasonal variables. A system and computer program product for automated forecasting of cash flow are also disclosed.

Computer-implemented method, system, and computer program product for automated forecasting

Facial image bucketing is disclosed, whereby a query for facial image recognition compares the facial image against existing candidate images. Rather than comparing the facial image to each candidate image, the candidate images are organized or clustered into buckets according to their facial similarities, and the facial image is then compared to the image(s) in most-likely one(s) of the buckets. The organizing uses particular selected facial features, computes distance between the facial features, and selects ones of the computed distances to determine which facial images should be organized into the same bucket.

Facial image bucketing with expectation maximization and facial coordinates

Generating weights for biometric tokens in probabilistic matching systems is disclosed, where these weights are generated from computations performed on matched sets and unmatched sets of a reference data set. In an embodiment, scores from a similarity scoring function are distributed among bins, and a weight is computed for each bin as the log of (the matched set ratio/the unmatched set ratio), where the ratios are computed as the number of scores in a particular bin as compared to the total size of the set. The weights may then be used subsequently with scores computed by the scoring function to assess confidence of a computed similarity score, and are directed toward making the output of the probabilistic matching system more data-driven and more accurate.

Generating weights for biometric tokens in probabilistic matching systems

A record is received including a token without a corresponding predetermined weight. Information pertaining to the received token is retrieved from at least one of external reference information and historic statistics. A token with a predetermined weight closest to the received token is determined based on the retrieved information. The predetermined weight of the closest token is assigned to the received token and data is matched based on the assigned weight of the received token.

Weight adjustment in a probabilistic matching system based on external demographic data

Growing community of inventors

Austin, TX, United States of America

Yinle Zhou