Abstract: Herein is resource-constrained feature enrichment for analysis of parse trees such as suspicious database queries. In an embodiment, a computer receives a parse tree that contains many tree nodes. Each tree node is associated with a respective production rule that was used to generate the tree node. Extracted from the parse tree are many sequences of production rules having respective sequence lengths that satisfy a length constraint that accepts at least one fixed length that is greater than two. Each extracted sequence of production rules consists of respective production rules of a sequence of tree nodes in a respective directed tree path of the parse tree having a path length that satisfies that same length constraint. Based on the extracted sequences of production rules, a machine learning model generates an inference. In a bag of rules data structure, the extracted sequences of production rules are aggregated by distinct sequence and duplicates are counted.

Abstract: A method, system, and computer program product for false decline mitigation. The method includes obtaining an objective function associated with an issuer system; training a neural network, based on prior transaction data associated with one or more prior transactions, to optimize the objective function; providing the trained neural network; receiving transaction data generated, based on one or more case creation (CC) rules, during processing of a transaction associated with an account identifier; processing, using the trained neural network, the transaction data to generate an exclude account list including the account identifier; receiving subsequent transaction data associated with a subsequent transaction associated with the account identifier; and authorizing, based on the exclude account list and the account identifier, the subsequent transaction associated with the account identifier without applying one or more real-time decisioning (RTD) rules to the subsequent transaction.

Abstract: Techniques are described herein for performing efficient matrix multiplication in architectures with scratchpad memories or associative caches using asymmetric allocation of space for the different matrices. The system receives a left matrix and a right matrix. In an embodiment, the system allocates, in a scratchpad memory, asymmetric memory space for tiles for each of the two matrices as well as a dot product matrix. The system proceeds with then performing dot product matrix multiplication involving the tiles of the left and the right matrices, storing resulting dot product values in corresponding allocated dot product matrix tiles. The system then proceeds to write the stored dot product values from the scratchpad memory into main memory.

Abstract: Disclosed is an improved approach to implement anomaly detection, where an ensemble detection mechanism is provided. An improvement is provided for the KNN algorithm where scaling is applied to permit efficient detection of multiple categories of anomalies. Further extensions are used to optimize local anomaly detection.

Abstract: Herein is resource-constrained feature enrichment for analysis of parse trees such as suspicious database queries. In an embodiment, a computer receives a parse tree that contains many tree nodes. Each tree node is associated with a respective production rule that was used to generate the tree node. Extracted from the parse tree are many sequences of production rules having respective sequence lengths that satisfy a length constraint that accepts at least one fixed length that is greater than two. Each extracted sequence of production rules consists of respective production rules of a sequence of tree nodes in a respective directed tree path of the parse tree having a path length that satisfies that same length constraint. Based on the extracted sequences of production rules, a machine learning model generates an inference. In a bag of rules data structure, the extracted sequences of production rules are aggregated by distinct sequence and duplicates are counted.

Abstract: Techniques are provided for sparse ensembling of unsupervised machine learning models. In an embodiment, the proposed architecture is composed of multiple unsupervised machine learning models that each produce a score as output and a gating network that analyzes the inputs and outputs of the unsupervised machine learning models to select an optimal ensemble of unsupervised machine learning models. The gating network is trained to choose a minimal number of the multiple unsupervised machine learning models whose scores are combined to create a final score that matches or closely resembles a final score that is computed using all the scores of the multiple unsupervised machine learning models.

Abstract: Herein are approaches for self-optimization of a database management system (DBMS) such as in real time. Adaptive just-in-time sampling techniques herein estimate database content statistics that a machine learning (ML) model may use to predict configuration settings that conserve computer resources such as execution time and storage space. In an embodiment, a computer repeatedly samples database content until a dynamic convergence criterion is satisfied. In each iteration of a series of sampling iterations, a subset of rows of a database table are sampled, and estimates of content statistics of the database table are adjusted based on the sampled subset of rows. Immediately or eventually after detecting dynamic convergence, a machine learning (ML) model predicts, based on the content statistic estimates, an optimal value for a configuration setting of the DBMS.

Abstract: The present disclosure relates to methods, systems, and apparatuses for providing electronic communications to client devices based on clustering and filtering candidates for inclusion in the electronic communications based on programmatically generated correlation metrics and thresholds associated with the clustering.

Abstract: System and methods include obtaining data, over the Internet, associated with a plurality of Wi-Fi networks each Wi-Fi network having one or more access points and each Wi-Fi network being associated with a customer of one or more service providers; aggregating and filtering the data; analyzing the aggregated and filtered data for the network condition of each of the plurality of customers of one or more service providers; determining an internet service provider (ISP) outage based on a plurality of factors; and performing one of a plurality of resolution or notification actions.

Abstract: Herein, a computer generates and evaluates many preprocessor configurations for a window preprocessor that transforms a training timeseries dataset for an ML model. With each preprocessor configuration, the window preprocessor is configured. The window preprocessor then converts the training timeseries dataset into a configuration-specific point-based dataset that is based on the preprocessor configuration. The ML model is trained based on the configuration-specific point-based dataset to calculate a score for the preprocessor configuration. Based on the scores of the many preprocessor configurations, an optimal preprocessor configuration is selected for finally configuring the window preprocessor, after which, the window preprocessor can optimally transform a new timeseries dataset such as in an offline or online production environment such as for real-time processing of a live streaming timeseries.

Abstract: Systems, methods, and computer program products may store, in a distributed cache, a rule associated with a plurality of accounts in a Real-Time Payments (RTP) network, the rule being stored in association with account data associated with the plurality of accounts; receive an account level exclusion directive associated with the account; store, in the distributed cache, the account level exclusion directive in association with the account; receive transaction data associated with a transaction in the RTP network between the account and another account; retrieve, from the distributed cache, the rule, the account level exclusion directive, and the account data associated with the account; exclude, based on the account level exclusion directive, use of the rule for processing the transaction; and process, without applying the rule, the transaction in the RTP network.

Abstract: System and methods include obtaining Wi-Fi network data, over the Internet, associated with a plurality of Wi-Fi networks each Wi-Fi network having one or more access points and each Wi-Fi network being associated with a customer of one or more service providers and obtaining customer data for each customer associated with the plurality of Wi-Fi networks, the customer data including call-ins made by customers; aggregating and filtering the data; analyzing the aggregated and filtered data including correlating the call-ins made by customers to the Wi-Fi network data; predicting customer call-ins based on correlations made between the call-ins made by customers and the Wi-Fi network data; and initiating a customer outreach workflow prior to a predicted customer call-in.

Abstract: System and methods include obtaining data, over the Internet, associated with a plurality of Wi-Fi networks each Wi-Fi network having one or more access points and each Wi-Fi network being associated with a customer of one or more service providers; aggregating and filtering the data; analyzing the aggregated and filtered data based on one or more use cases; determining any of predictions and alerts for the one or more use cases based on the analyzing; and performing one or more actions based on the any of predictions and alerts.

Abstract: Techniques for computing global feature explanations using adaptive sampling are provided. In one technique, first and second samples from an dataset are identified. A first set of feature importance values (FIVs) is generated based on the first sample and a machine-learned model. A second set of FIVs is generated based on the second sample and the model. If a result of a comparison between the first and second FIV sets does not satisfy criteria, then: (i) an aggregated set is generated based on the last two FIV sets; (ii) a new sample that is double the size of a previous sample is identified from the dataset; (iii) a current FIV set is generated based on the new sample and the model; (iv) determine whether a result of a comparison between the current and aggregated FIV sets satisfies criteria; repeating (i)-(iv) until the result of the last comparison satisfies the criteria.

Abstract: System and methods include obtaining data, over the Internet, associated with a plurality of Wi-Fi networks each Wi-Fi network having one or more access points and each Wi-Fi network being associated with a customer of one or more service providers; aggregating and filtering the data; analyzing the aggregated and filtered data for the network condition of each of the plurality of customers of one or more service providers; determining an internet service provider (ISP) outage based on a plurality of factors; and performing one of a plurality of resolution or notification actions.

Abstract: Techniques are described for executing machine learning models trained for specific operators with feature values that are based on the actual execution of a workload set. The machine learning models generate an estimate of benefit gain/cost for executing operations on data portions in the alternative encoding format. Such data potions may be sorted based on the estimated benefit, in an embodiment. Using cost estimation machine learning models for memory space, the data portions with the most benefits that comply with the existing memory space constraints are recommended and/or are automatically encoded into the alternative encoding format.

Abstract: Systems and methods of detecting a parallel Wi-Fi network or a parallel Wi-Fi access point include operating a new Wi-Fi network at a location; analyzing Wi-Fi at the location; determining whether there is a parallel Wi-Fi network or a parallel Wi-Fi access point operating at the location with the new Wi-Fi network based on the analyzing; and, responsive to determining there is the parallel Wi-Fi network or the parallel Wi-Fi access point at the location, performing one or more of i) causing resolution of the parallel Wi-Fi network or the parallel Wi-Fi access point and ii) providing a notification to a user associated with the location.

Abstract: System and methods include obtaining Wi-Fi network data, over the Internet, associated with a plurality of Wi-Fi networks each Wi-Fi network having one or more access points and each Wi-Fi network being associated with a customer of one or more service providers and obtaining customer data for each customer associated with the plurality of Wi-Fi networks, the customer data including call-ins made by customers; aggregating and filtering the data; analyzing the aggregated and filtered data including correlating the call-ins made by customers to the Wi-Fi network data; predicting customer call-ins based on correlations made between the call-ins made by customers and the Wi-Fi network data; and initiating a customer outreach workflow prior to a predicted customer call-in.

Abstract: Techniques are described for executing machine learning models trained for specific operators with feature values that are based on the actual execution of a workload set. The machine learning models generate an estimate of benefit gain/cost for executing operations on data portions in the alternative encoding format. Such data potions may be sorted based on the estimated benefit, in an embodiment. Using cost estimation machine learning models for memory space, the data portions with the most benefits that comply with the existing memory space constraints are recommended and/or are automatically encoded into the alternative encoding format.

Abstract: The present disclosure relates to methods, systems, and apparatuses for determining item recommendations and receiving dynamic modifications to an item recommendation algorithm. The method includes receiving electronic data indicating a set of items, generating, using a recommendation engine executing on a processor, a first set of one or more item recommendations from the set of items, causing a client interface to be generated, the client interface comprising the one or more item recommendations and a plurality of interface controls, wherein selection of one of the plurality of interface controls causes a weight adjustment indication to be transmitted for at least one of the plurality of weights, receiving the weight adjustment indicator, adjusting at least one weight of the plurality of weights associated with the weight adjustment indicator, and generating a second set of one or more item recommendations using the adjusted at least one weight.