Abstract:
A system and computer-implemented method for analyzing chip card transactions to identify defective chip cards and/or defective chip readers in need of replacement. Constraints are established to define a subset of card transactions. From a full set of card transactions the subset is identified consisting of each card transaction falling within the constraints and occurring at a merchant having a chip reader. From this subset the unique chip cards are identified, and for each unique chip card a percentage of fallback transactions is calculated. The percentage of fallback transactions is compared to a maximum value, and if the percentage of fallback transactions exceeds the maximum value, the chip card is identified as defective. Each defective chip card is reported to the card issuer, along with at least a recommendation to replace the defective chip card. A similar process may be used to identify defective chip readers of particular merchants.
Abstract:
A system and computer-implemented method for analyzing chip card transactions to identify defective chip cards and/or defective chip readers in need of replacement. Constraints are established to define a subset of card transactions. From a full set of card transactions the subset is identified consisting of each card transaction falling within the constraints and occurring at a merchant having a chip reader. From this subset the unique chip readers are identified, and for each unique chip reader a percentage of fallback transactions is calculated. The percentage of fallback transactions is compared to a maximum value, and if the percentage of fallback transactions exceeds the maximum value, the chip reader is identified as defective. Each defective chip reader is reported to the merchant, along with at least a recommendation to replace the defective chip reader. A similar process may be used to identify defective chip cards.
Abstract:
Systems and methods are provided for processing messages from users, via interactive interfaces, requesting support relating to features of applications available to the users. In connection therewith, the systems and methods normalize and score the user messages, and use the scores, in combination with scores for historical messages or scores for crowdsourced messages, to identify appropriate response messages for transmittal to the users. In various aspects, the crowdsourced solutions can be voted by both users and domain experts, and also verified by the domain experts. If a solution is verified it will be flagged and it can be included into a reference solution database as a standard response. However, when the scores assigned to the messages do not produce suitable results, a request for additional information relating to the issue described by the user is transmitted via the interactive interface.
Abstract:
Systems and methods are provided for performing anomaly detection. One example method relates to transaction data including fraud scores output by a fraud score model generated by a machine learning system. The method includes determining, by a computing device, divergence values for multiple segments of payment accounts between baseline distributions of fraud scores and current distributions of fraud scores for the segments and detecting, by the computing device, at least one of the divergence values for at least one of the multiple segments as an anomaly. The method also includes categorizing, by the computing device, the detected anomaly into one of multiple categories, whereby the one of the multiple categories is indicative of a type of issue associated with the detected anomaly.
Abstract:
Systems and methods are provided for scoring support messages from users indicative of the likelihood of escalation of the messages, upon which the messages may be prioritized. One exemplary method includes receiving, from a user, a support message related to a payment service provider and generating an escalation score for the support message based on a temporal factor associated with a duration associated with the support message, a source factor for the support message, and a text content factor of the support message. The exemplary method further includes identifying a likelihood of escalation of the support message based on the escalation score, whereby a support representative assigned to the support message is able to prioritize the support message over at least one other support message based on the likelihood of escalation for the support message.
Abstract:
Systems and methods are provided for use in distributing code testing tasks among multiple testers, and incentivizing testing with rewards. One exemplary method includes testing, by a computing device, a code set, where the testing is performed by a tester associated with a profile, and receiving, by the computing device, peer tester feedback based on the testing of the code set, where the peer tester feedback is associated with at least one peer tester profile. The method also includes receiving, by the computing device, a developer decision based on the testing of the code set and/or the peer tester feedback, and rewarding, by the computing device, the profile of the tester and/or the at least one peer tester profile when the developer decision agrees with the testing of the code set and/or the tester feedback associated with the at least one peer tester profile.
Abstract:
Systems and methods are provided for use in distributing code testing tasks among multiple testers, and incentivizing testing with rewards. One exemplary method includes testing, by a computing device, a code set, where the testing is performed by a tester associated with a profile, and receiving, by the computing device, peer tester feedback based on the testing of the code set, where the peer tester feedback is associated with at least one peer tester profile. The method also includes receiving, by the computing device, a developer decision based on the testing of the code set and/or the peer tester feedback, and rewarding, by the computing device, the profile of the tester and/or the at least one peer tester profile when the developer decision agrees with the testing of the code set and/or the tester feedback associated with the at least one peer tester profile.
Abstract:
The disclosure relates to methods and systems of joining data structures based on a composite similarity score (CSS). For example, a computer system may use a plurality of similarity models to generate respective similarity scores. Each similarity score may be a metric that indicates a confidence that a first data value of a first data record is similar to a second data value of a second data record. The computer system may generate the CSS based on the plurality of similarity sub-scores. The CSS may indicate a confidence that the records being compared are similar. Thus, the CSS may be used to detect similar data records across different data structures. The disclosure also relates to a string similarity model that detects similarity among strings without respect to an order of words in each string and in a way that tolerates errors or omissions in one or both strings.
Abstract:
Systems and methods are provided for processing messages from users, via interactive interfaces, requesting support relating to features of applications available to the users. In connection therewith, the systems and methods normalize and score the user messages, and use the scores, in combination with scores for historical messages or scores for crowdsourced messages, to identify appropriate response messages for transmittal to the users. In various aspects, the crowdsourced solutions can be voted by both users and domain experts, and also verified by the domain experts. If a solution is verified it will be flagged and it can be included into a reference solution database as a standard response. However, when the scores assigned to the messages do not produce suitable results, a request for additional information relating to the issue described by the user is transmitted via the interactive interface.
Abstract:
Systems and methods are provided for evaluating aggregate merchant sets, which are often generated by a payment network. One exemplary method includes accessing, by a computing device, a monitor score and a volatility score for an aggregate merchant set representative of multiple merchants having at least one disparate parameter in a transaction data structure, fuzzy sets for the monitor score and the volatility score comprising linguistic values, and inference rules that use the linguistic values in logical operations. The method also generally includes determining degrees of membership of the monitor score and volatility score to the associated fuzzy sets and generating an evaluation index based on the inference rules and the degrees of membership to the fuzzy sets, thereby providing an indication of a propriety of the aggregation of said multiple merchants.