Abstract: Methods, systems and apparatuses, including computer programs encoded on computer storage media, are provided for generating prediction models related to targeting and acquiring customers. Thousands of variables of historical data, including data for prospects and external data, are used to train the prediction models. The variables are pre-processed, then sensitivity analysis is performed on the input variables with respect to the target. The variables with the most influence on the target are selected and added to the feature set used for training a prediction model.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating weather forecasting modules from historical weather data, including unstructured and structured data. The weather forecasting modules each comprise at least one model, such as a neural network, that generates a forecast from input weather data. Each module may be focused on a particular region, weather variable, and or forecasting time period. Unstructured data may be analyzed by the system to generate weather-related variables which are combined with structured weather data to generate a combined weather feature set that is input to the model. Alternatively, unstructured data may be input directly in the module, with or without preprocessing. The weather forecasts can then be used to forecast various power-generation related variables or events, including power generation, electrical load, etc.

Abstract: To extract necessary information, documents are received and classified, converted to text, and stored in a database. A request for information is then received, and relevant documents and/or document passages are selected from the stored documents. The needed information is then extracted from the relevant documents. The various processes use one or more artificial intelligence (AI), image processing, and/or natural language processing (NLP) techniques as well as knowledge-based and rule-based techniques.

Abstract: To extract necessary information, documents are received, converted to text, and stored in a database. A request for information is then received, and relevant documents and/or document passages are selected from the stored documents. The needed information is then extracted from the relevant documents. The various processes use one or more artificial intelligence (AI), image processing, and/or natural language processing (NLP) techniques.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, are provided for processing claims using both unstructured and structured policy documents, claim data, and customer and policy data, in conjunction with automatic requests for human intervention. Policy rules, benefit calculation formulae, necessary data points, and benefit requirements are extracted from policy documents using NLP and AI techniques. Unstructured claim data is converted to a structured form using natural language processing, information extraction, and AI techniques to identify and extract relevant information, including values for the data points and benefit conditions, then the combined structured data and converted unstructured data is processed to get all values for the data points and applicable benefit conditions.

Abstract: Methods and systems are provided for clustering data for use in training models to predict a loss metric for insurance. The historical data is cleaned and aggregated to a quarterly time granularity and a zip code geographic granularity, and features on which to generate the clusters are selected. Clusters are generated using one or more clustering algorithms, evaluated, and the best set of clusters is selected. Clusters may be grouped together based on cluster characteristics. Each cluster or group of clusters is used to train a development model and a forecast model for the loss metric. The accuracy of the development and forecast models is evaluated, and the clustering process is repeated until the accuracy and stability of the development and forecast models is sufficient. At each iteration, historical data may be removed and/or hyperparameters of the clustering algorithms may be adjusted.

Abstract: Methods and systems are provided for predicting and forecasting loss metrics for insurance. One or more models are created to generate development curves to predict ultimate losses for aggregations of long-tail losses, such as bodily injury claim payouts based on the first few months of payout data and other relevant variables. The relevant variables include internal data about policyholders and claims, and external data. Historical data, including potential influential variables and a target, are used to train a predictive development model. The variables are pre-processed and aggregated to an accident-month granularity, then feature reduction techniques are applied to determine the variables that exert the most influence on the target. Dimensionality reduction techniques are then applied to the remaining variables. The most influential variables and the variables created by dimension reduction are used as the input features to train the development model.

Abstract: Methods, systems and apparatuses, including computer programs encoded on computer storage media, are provided for processing claims using both unstructured and structured policy documents and claim data. Policy rules, benefit calculation formulae, necessary data points, and benefit requirements are extracted from policy documents. Unstructured claim data is converted to a structured form using natural language processing, information extraction, and AI techniques to identify and extract relevant information, including values for the data points and benefit conditions, then the combined structured data and converted unstructured data is processed to get all values for the data points and applicable benefit conditions. The relevant claim information is then further processed according to the policy rules and benefit calculation formulae to generate a benefit payment amount and entitled additional benefits.

Abstract: A system includes at least one server implementing a weather forecast engine and in communication with a network, the server to access satellite imagery, published weather predictions, and local measured data via the network; the weather forecast engine to train regional modules using the satellite imagery, published weather predictions, and local measured data; and the weather forecast engine to apply the satellite imagery, published weather predictions, and local measured data to the trained regional modules to obtain regional forecasts. A method for forecasting a weather indicator includes receiving satellite imagery; processing the satellite imagery to generate a weather feature set; applying the weather feature set to a regional module of a weather forecast engine; and forecasting the weather indicator with the weather forecast engine.

Abstract: A system for merging data into a database is disclosed. During operation, the system may fetch a set of data from a data source external to the database. The system may determine that the fetched set of data is unstructured data, and then transform the fetched set of data into structured data. The system may also determine one or more lowest denominators for the fetched set of data, determine that the fetched set of data does not meet the one or more lowest denominators, and transform the fetched set of data to meet the one or more lowest denominators. The system may further determine one or more joinable keys for the fetched set of data, and merge the fetched set of data into the database.

Abstract: A system for merging data into a database is disclosed. During operation, the system may fetch a set of data from a data source external to the database. The system may determine that the fetched set of data is unstructured data, and then transform the fetched set of data into structured data. The system may also determine one or more lowest denominators for the fetched set of data, determine that the fetched set of data does not meet the one or more lowest denominators, and transform the fetched set of data to meet the one or more lowest denominators. The system may further determine one or more joinable keys for the fetched set of data, and merge the fetched set of data into the database.