Abstract: In one example, a non-transitory computer-readable storage medium with program instructions for determining anomalies in machine learning models and impact on business output data thereof is disclosed. The method accesses machine learning model variables for a machine learning model, and determines a deviation in behavior of the machine learning model by performing statistical analysis on each machine learning model variable to identify statistical differences between machine learning model variable data captured in a given time window and data captured in a previous time window at the same time of a prior day, prior week, etc. If statistical differences exist, the method performs anomaly detection to determine whether the statistical differences are an anomaly. If so, the method determines whether the anomaly causes an impact on business decision output data, and if so, identifying a root cause and generating a notification alert for corrective action.

Abstract: Systems and methods for rule optimization are disclosed. In accordance with aspects, a method may include providing a segment rule, where the segment rule uses a machine learning model score associated with a data record and a scaler value to evaluate data records and the segment rule is configured to evaluate data records categorized into a corresponding segment of the segment rule by attributes of the data records; receiving, at the segment rule, a categorized set of data records, wherein each data record in the categorized set of data records is categorized in the corresponding segment of the segment rule based on attributes of the data records; iteratively evaluating, by the segment rule, each received data record with a range of scaler values, where the iteratively evaluating produces a plurality of outputs of the segment rule; and determining an optimal output from the plurality of outputs.

Abstract: A method for utilizing a graph path cache to facilitate real-time data consumption by a plurality of machine learning models is disclosed. The method includes receiving an input from a source, the input relating to a request to characterize a data element; retrieving a data attribute that corresponds to the data element from a data management system; determining, in real-time using the graph path cache, a graph attribute that corresponds to the data element by performing deep link analysis on a graph database; executing, in real-time, a model by using the data attribute and the graph attribute, the model corresponding to the request in the input; and transmitting, in real-time, a result of the executed model to the source in response to the input.

Abstract: Systems and methods for frequent machine learning model retraining and rule optimization are disclosed. In accordance with aspects, a method may include generating a challenger machine learning model based on a production machine learning model; training the challenger machine learning model on a plurality of datasets; scoring historical data with the challenger machine learning model, wherein the scoring produces a respective score for each record of a plurality of records in the historical data; determining that the challenger model performs within predetermined thresholds based on the scoring; selecting an optimal scaler value for a rule based on execution of the rule with a range of scaler values applied to the respective score for each record of the plurality of records evaluated by the rule; determining that the optimal scaler value outperforms a production scaler value; and promoting the challenger model and the optimal scaler value to a production environment.

Abstract: Systems and methods for frequent machine learning model retraining and rule optimization are disclosed. In accordance with aspects, a method may include retrieving, from a data store, a plurality of datasets; generating a challenger machine learning model, wherein the challenger machine learning model is generated from a production machine learning model, and includes variables and variable weights included in the production machine learning model; training the challenger machine learning model with the plurality of datasets; adjusting the variable weights of the challenger machine learning model based on patterns in the plurality of datasets determined by the challenger machine learning model; performing a comparative analysis between the challenger model and the production model; and promoting the challenger model to a production environment based on the comparative analysis.

Abstract: A method for utilizing a graph path cache to facilitate real-time data consumption by a plurality of machine learning models is disclosed. The method includes receiving an input from a source, the input relating to a request to characterize a data element; retrieving a data attribute that corresponds to the data element from a data management system; determining, in real-time using the graph path cache, a graph attribute that corresponds to the data element by performing deep link analysis on a graph database; executing, in real-time, a model by using the data attribute and the graph attribute, the model corresponding to the request in the input; and transmitting, in real-time, a result of the executed model to the source in response to the input.

Abstract: Various methods, apparatuses, and media for implementing a fraud machine learning model execution module are provided. A processor generates a plurality of machine learning models. The processor generates historical aggregate data based on prior transaction activities of a customer from a plurality of databases for transactions. The processor also tracks activities of the customer during a new transaction authorization process and generates a transaction data; integrates the transaction data with the historical aggregate data; executes each of said machine learning models using the integrated transaction data and the historical aggregate data to generate a fraud score and stores the fraud score into the memory; and determines whether the new transaction is fraudulent based on the generated fraud score.

Abstract: Various methods, apparatuses, and media for implementing a check fraud detection module are provided. A processor parses received digital image of a check into separate portions, one of the portions including a signature of an account holder. The processor applies a machine learning model to generate a new 128-dimensional embedding of the signature of the account holder parsed from the received digital image of the check and compares it preauthorized historical reference 128-dimensional embedding of the signature stored onto a database. The processor generates, based on comparing, a similarity score between the new 128-dimensional embedding of the signature and the preauthorized historical reference 128-dimensional embedding of the signature; and identifies whether the received check is fraudulent or not based on the generated similarity score.

Abstract: Various methods, apparatuses, and media for implementing a fraud machine learning model execution module are provided. A processor generates a plurality of machine learning models. The processor generates historical aggregate data based on prior transaction activities of a customer from a plurality of databases for transactions. The processor also tracks activities of the customer during a new transaction authorization process and generates a transaction data; integrates the transaction data with the historical aggregate data; executes each of said machine learning models using the integrated transaction data and the historical aggregate data to generate a fraud score and stores the fraud score into the memory; and determines whether the new transaction is fraudulent based on the generated fraud score.