Abstract: An apparatus for generating a generalized linear model structure definition by generating a gradient boosted tree model and separating each decision tree into a plurality of indicator variables upon which a dependent variable of the generalized linear model depends.

Abstract: The probabilistic accumulation method is an independent and comprehensive approach for validating third party catastrophe models. The method starts with a standard technique, namely a limited scenario accumulation analysis, and extends the approach via a novel sampling methodology to evaluate the third part models against a significantly larger dataset. The sampling approach includes a technique for extending the fixed frequency and severity assumption used by the vendor catastrophe models. The result is more complete set of loss estimates against which to evaluate the vendor model output.

Abstract: Methods, apparatuses, systems, computing entities, and/or the like are provided. An example method may include retrieving a base image associated with at least one software application; generating a customized base image based at least in part on conducting at least one operational verification operation on the base image; generating a validated base image based at least in part on conducting at least one operational testing operation on the customized base image; generating a release note data object associated with the validated base image; and performing one or more image release operations by releasing the validated base image and the release note data object to at least one client system.

Abstract: Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for programmatically predicting policy transactions using machine learning.

Abstract: Home telematics devices are engineered to identify unique device signatures for all appliances, fixtures, and so on that generate voltage noise, pressure waves, and acoustic responses throughout a property. The device signatures comprise the inventory of devices in the insured's home and are used to create an electronic record of the devices that assists him in filing a claim with an insurer that is quick and easy after a theft or total loss. Using the device signatures provided by home telematics devices' sensing an itemization technology, fraud detection is also possible. Additionally, analytics software predicts possible failure by analyzing the device signatures.

Abstract: Methods, apparatuses, systems, computing entities, and/or the like are provided. An example method may include retrieving software development data associated with a software application; receiving modular configuration data from a client system; determining application usage data based at least in part on a user profile of the client system that is associated with the software application; generating a release note data object based at least in part on at least one of the software development data, the modular configuration data, and the application usage data; and performing one or more software application release operations by transmitting the release note data object to the client system.

Abstract: There is a need for more effective and efficient predictive data analysis. Various embodiments of the present invention address one or more of the noted technical challenges. In one example, a method for generating a neutralized prediction model includes accessing an initial prediction model generated using an initial training data object, performing a randomized shuffling of the initial training data object to generate a shuffled training data object, generating randomized predictions by processing the shuffled training data object using the initial prediction model, performing a neutralization of the initial training data object to generate a neutralized training data object, and generating the neutralized prediction model based at least in part on the neutralized training data object and the randomized predictions.

Abstract: There is a need for solutions that generates a temporally dynamic prediction for a particular prediction input. This need can be addressed by, for example, processing the prediction input using each of a plurality of temporally trained machine learning models to generate a corresponding model-specific prediction inference of a plurality of model-specific prediction inferences and processing the plurality of model-specific prediction inferences using an ensemble model to generate the temporally dynamic prediction for the prediction input.

Abstract: Methods, apparatuses, systems, computing entities, and/or the like are provided. An example method may include determining per-application configuration data associated with a software application; determining per-client configuration data associated with a client system; determining per-application per-client configuration data associated with the software application and the client system; generating modular configuration data based at least in part on at least one of the per-application configuration data, the per-client configuration data, and the per-application per-client configuration data; generating a releasable software application based at least in part on the modular configuration data; and performing one or more software release operations by transmitting the releasable software application to the client system.

Abstract: There is a need for more effective and efficient secure data transmission. This need can be addressed by, for example, solutions for secure data transmission that utilize per-user-functionality secret shares. In one example, a method includes generating a hashed user identifier based on a received user identifier; transmitting the hashed user identifier to an external computing entity; and receiving a data retrieval secret share from the external computing entity, wherein: (i) the data retrieval secret share is selected from a plurality of per-user-functionality secret shares, (ii) the plurality of per-user-functionality secret shares are generated based on a secret value, (iii) the secret value is generated based on the hashed user identifier, (iv) the secret value is used to generate a user data private key, and (v) the external computing entity is configured to encrypt user-provided data using the user data private key prior to transmission of the encrypted user-provided data.

Abstract: Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for selecting a test suite for an API. In one embodiment, a computing entity or apparatus is configured to receive test patterns and heuristics, receive an input API, the input API comprising API specifications, parse the input API to extract the API specifications, and based at least in part on the extracted API specifications and the test patterns and heuristics, select a test suite, wherein the test suite is programmatically generated using a machine learning model and comprises one or more test routines, one or more data values, and one or more expected results.

Abstract: An apparatus comprising a communications interface configured to communicate over one or more networks, at least one processor and at least one memory including program code is provided. The at least one memory and the program code configured to, with the processor, cause the apparatus to at least receive, via the communications interface, an interparty transaction request. The interparty transaction request corresponds to an interparty transaction and identifying a first party and a second party. The apparatus generates a smart contract based on the interparty transaction request; stores a data entry indicating the generation of the smart contract to a distributed ledger; executes the smart contract to cause settlement of the interparty transaction between the first party and the second party; and stores a data entry indicating the settlement of the interparty transaction to the distributed ledger.

Abstract: A system is engineered to facilitate calculation of predicted perils connected with a ridesharing vehicle. The system facilitates premium endorsement that provides higher coverage than is provided under conventional products and allows drivers to work directly with their personal lines insurer in reviewing their coverage and filing a claim in the event of an accident. The subject matter facilitates higher limits while including a post-policy period audit that allows a reconciliation of high-use or high-risk driving with appropriate retroactive rate adjustments. The system also facilitates retroactive rate adjustments that would compare a policyholder’s time/distance driven or collected telematics data (including time or distance driven in each driving period) to the group average or other historical underwriting data.

Abstract: Home telematics devices are engineered to identify unique device signatures for all appliances, fixtures, and so on that generate voltage noise, pressure waves, and acoustic responses throughout a property. The device signatures comprise the inventory of devices in the insured's home and are used to create an electronic record of the devices that assists him in filing a claim with an insurer that is quick and easy after a theft or total loss. Using the device signatures provided by home telematics devices' sensing an itemization technology, fraud detection is also possible. Additionally, analytics software predicts possible failure by analyzing the device signatures.