Abstract: Systems and methods for generating tables using data associated with records. For example, a system may store the data associated with the record in one or more databases. The system may then generate tables associated with fields of the record, where the tables indicate updates and/or changes to the fields. For instance, when changes are made to a field of the record, the system may update the table to indicate the changes, times at which the changes occurred, identifiers of users that made the changes, reasons for the changes, and/or so forth. The system may further update a version of the record when updates and/or changes are made to the fields. Furthermore, the system may update the tables to indicate versions of the record when the updates and/or changes occurred to the fields.

Abstract: Systems and methods for medication fillings management are disclosed. For example, user information and/or refill schedules associated with users may be utilized to predict which users are likely to miss a medication refill. The presently disclosed systems and methods may determine health indicators associated with users and, by utilizing one or more machine learning techniques, determine which health indicators, alone or in combination, are associated with users prone to missing refills. As such, the system may predict users that are likely to miss a refill and may generate preemptive, targeted refill reminders in order to prevent the missed refill before it occurs.

Abstract: Systems and methods for models utilizing siloed data are disclosed. For example, data stored with and/or available to one or more systems may be siloed such that it may not be aggregated and/or shared with other systems. The presently-disclosed systems and methods utilize predictive layers and models to allow each system to predict outcomes using its own data and then models are shared between systems to allow each associated system to gain the benefits of the data of other systems without aggregating such data or otherwise sharing the data.

Abstract: The present disclosure describes methods and systems for machine learning models utilized for diagnosis suspecting. These methods and systems utilize machine learning models may be trained to diagnose diseases or conditions. The models may be trained with data from disparate sources that are aggregated and formatted to be utilized in these models.

Abstract: Systems and methods for data unfolding are disclosed. For example, it may be desirable or necessary to increase a data set, such as for increasing accuracy of one or more predictive models. Data set proliferation without introducing unnecessary bias may be important for increasing such accuracy. Described herein are system and methods that allow for data set proliferation by generating records based on whether an event occurred with respect to an entity during multiple time intervals. A record may be generated for each time interval and the associated data may be unfolded and disassociated, at least partly, from other records related to the entity. Those records may then be used for data analytics and/or predictive model generation, for example.

Abstract: Systems and methods for segmenting claims data for actuarial modeling are disclosed. For example, traditional actuarial models determine the money paid out in a given month and estimate future months based at least in part on the money paid out, but these traditional models fail when dealing with volatile data for new markets and/or expanding member base. The presently-disclosed systems and methods segments data into incremental metrics and uses the segmented data to provide more granular information about the claims. Increasing granularity in data not only increases accuracy for predictions but the new actuarial model developed using segmented data may also be used as market analysis tools to predict favorable new markets to enter.

Abstract: Systems and methods for generating document content using data analysis. For example, a system may store data representing one or more documents, where a document is associated with a type of user and fields. The system may send the data representing the document to an electronic device. Additionally, the system may receive, from the electronic device, data representing information input into the document. Using the information, the system may select various fields for the document and send, to the electronic device, data representing the fields. Furthermore, the system may analyze the information to determine a score associated with the document. If the score does not satisfy a threshold score, the system may continue to select fields using the information and send, to the electronic device, data representing the fields. However, if the score satisfies the threshold score, the system may determine that the document is complete.

Abstract: A method including determining a first bid for a healthcare plan and a second bid for the healthcare plan. A bid-pricing tool is configured to utilize one or more first components to determine the first bid and one or more second components to determine the second bid, respectively. A bid difference between the first bid and the second bid includes at least a monetary difference in premiums paid by members of the first bid for the healthcare plan and members of the second bid for the healthcare plan. One or more third components are determined based at least in part on the bid difference to determine a third bid for the healthcare plan. A second bid difference is determined between at least one of the first bid and the third bid or the second bid and the third bid.

Abstract: Systems and methods for generating tables using data associated with records. For example, a system may store the data associated with the record in one or more databases. The system may then generate tables associated with fields of the record, where the tables indicate updates and/or changes to the fields. For instance, when changes are made to a field of the record, the system may update the table to indicate the changes, times at which the changes occurred, identifiers of users that made the changes, reasons for the changes, and/or so forth. The system may further update a version of the record when updates and/or changes are made to the fields. Furthermore, the system may update the tables to indicate versions of the record when the updates and/or changes occurred to the fields.

Abstract: Techniques and architectures for clustering health care providers based on data regarding services that have previously been provided by health care providers are described herein. For example, the techniques and architectures may receive data from devices of health care providers regarding services that have been provided by the health care providers to patients. The techniques and architectures may perform various machine learning techniques, including clustering, to categorize health care providers into multiple clusters based on the services that were provided. Health care providers that lie within a cluster may be associated with a category of the cluster. While health care providers that lie outside a cluster, and have designated themselves as being associated with or are otherwise associated with a practice area that is associated with the cluster, may be flagged as potentially practicing outside an area that is designated by or otherwise associated with the health care providers.

Abstract: Systems and methods for models utilizing siloed data are disclosed. For example, data stored with and/or available to one or more systems may be siloed such that it may not be aggregated and/or shared with other systems. The presently-disclosed systems and methods generate and utilize predictive layers and models to allow each system to predict outcomes using its own data and then models are shared between systems to allow each associated system to gain the benefits of the data of other systems without aggregating such data or otherwise sharing the data.

Abstract: Systems and methods for models utilizing siloed data are disclosed. For example, data stored with and/or available to one or more systems may be siloed such that it may not be aggregated and/or shared with other systems. The presently-disclosed systems and methods generate and utilize predictive layers and models to allow each system to predict outcomes using its own data and then models are shared between systems to allow each associated system to gain the benefits of the data of other systems without aggregating such data or otherwise sharing the data.

Abstract: Systems and methods for transforming and pipelining data are disclosed. For example, it may be desirable to parse out usable data and to transform the usable data found in files that may be received from different sources and that may be in different file types. Described herein are system and methods that provide functionality to allow for determining a file type of a file, parsing out usable data from the file, performing a series of transformations on the usable data, and generating a pipeline that includes the series of transformations. The pipeline may be monitored for error detection.