Abstract: Systems and methods of monitoring for anomalous data records. The system conducts a method including: receiving a data record associated with at least one meta attribute to determine whether subsequent processing of the data record is warranted; generating an anomaly prediction for the data record based on a detection model and the at least one meta attribute associated with the data record, the detection model defined by a plurality of score distribution representations based on quantile bins and a dynamic quantile weight for providing an interim anomaly measure corresponding to respective score distribution representations, wherein the anomaly prediction is generated based on a combination of interim anomaly measures associated with respective meta attributes associated with the data record; and transmitting a signal representing the anomaly prediction for presentation at a user device for identifying one or more data records for subsequent data processes.

Abstract: Disclosed are systems, methods, and devices for data anomaly detection. A signal reflective of an input data set having a plurality of dimensions is received. Co-variance across said plurality of dimensions is assessed. Upon said assessing, at least a portion of the input data set is transformed into a dimensionality-reduced data set. For each given data point in the dimensionality-reduced data set, an anomaly score informative of whether said given data point is an anomaly is calculated.

Abstract: Risk levels for accounts are assessed based on account data for the accounts, including reconciliation status and balance values. For each of the accounts, risk criteria scores are assigned for a plurality of risk criteria, based at least in part on one or more of reconciliation status and balance value for the account, and a composite risk score is determined for the account based on a weighted summation of a selection of the risk criteria scores for the account. A density distribution of the composite risk scores is generated for an audit population of the accounts, and quantiles determined. Thresholds are identified based at least in part on the quantiles of the density distribution, and a risk rating assigned to each of the accounts in the audit population based at least in part on the composite risk score for that account as compared to the thresholds.

Abstract: Systems and methods of monitoring for anomalous data records. The system conducts a method including: receiving a data record associated with at least one meta attribute to determine whether subsequent processing of the data record is warranted; generating an anomaly prediction for the data record based on a detection model and the at least one meta attribute associated with the data record, the detection model defined by a plurality of score distribution representations based on quantile bins and a dynamic quantile weight for providing an interim anomaly measure corresponding to respective score distribution representations, wherein the anomaly prediction is generated based on a combination of interim anomaly measures associated with respective meta attributes associated with the data record; and transmitting a signal representing the anomaly prediction for presentation at a user device for identifying one or more data records for subsequent data processes.

Abstract: Systems for dynamically updating a priority queue for scheduling data operations associated with data records. A method includes: detecting event data meeting a threshold value for identifying a shift in data operation relevance and traversing a cascading data structure to identify an auditable entity corresponding to one or more data records associated with the event data, the one or more data records corresponding to at least one branch of the cascading data structure. The method includes generating an updated priority queue for scheduling data operations based on priority weights associated with branches of the cascading data structure, the updated priority queue based on event data corresponding to the identified auditable entity relative to event data associated with one or more records corresponding to other auditable entities and transmitting a signal for dynamically communicating the updated priority queue for scheduling data operations associated with data records of respective auditable entities.

Abstract: A memory management architecture in a testing environment including a memory cache and a hard drive is provided. The hard drive may be configured to receive a high-volume set of production data including computer-readable spreadsheet files in varied file formats. The memory cache comprised in the memory management architecture may be configured to receive and store from the hard drive a first subset of the high-volume set of production data. This form of retrieval allows for not having to receive from off-site or from an external source. The memory management architecture may also include a diagnostic tool that may be used for data analysis. The diagnostic tool may analyze and test the fields listed on the field list, for any errors and/or omissions. When the data analysis and testing is complete, the diagnostic tool may then generate a data analysis summary report based on the analysis.

Abstract: A memory management architecture in a testing environment including a memory cache and a hard drive is provided. The hard drive may be configured to receive a high-volume set of production data including computer-readable spreadsheet files in varied file formats. The memory cache comprised in the memory management architecture may be configured to receive and store from the hard drive a first subset of the high-volume set of production data. This form of retrieval allows for not having to receive from off-site or from an external source. The memory management architecture may also include a diagnostic tool that may be used for data analysis. The diagnostic tool may analyze and test the fields listed on the field list, for any errors and/or omissions. When the data analysis and testing is complete, the diagnostic tool may then generate a data analysis summary report based on the analysis.