Abstract: A model assessment service is disclosed. The model assessment service may evaluate model metrics for an evaluation dataset using ground truth data and model predictions. The model assessment service may compare model performance by, among other things, comparing metric values against threshold values or against metric values of other models. Using a customizable configuration file, the model comparison may comprise different ways to compare models and different ways to evaluate specific metrics. As an example, the model assessment service can assess whether a new candidate model is to replace a deployed production model.

Abstract: Methods and systems for predicting relevant items to be presented to a user in an online environment. The methods and systems described herein generate models based on previous item selections to determine an overall model useable to generate item recommendations. In some examples, an item-level and category-level Hawkes process may be used, modeling a combination of an exponential distribution for short-history effects and Gaussian mixture probabilities to account for extended time period effects.

Abstract: Methods and systems for providing a product bundle recommendation are disclosed. One method includes receiving a selection of a first product at a retail website, and identifying the first product in a product graph generated from historical add to cart data. The method includes, identifying, in the product graph: one or more edges from the initial product to secondary products; one or more edges from a similar product to one or more secondary-similar products; and one or more inferred edges from the initial product to one or more inferred secondary products. The method further includes forming a set of recommended products from the one or more secondary products, the one or more secondary-similar products, and the one or more inferred secondary products, and presenting a bundled product recommendation selected from among the set of recommended products.

Abstract: A method of extracting data from documents is provided. The method comprises receiving input of a number of documents and input of a schema of data items available for extraction from the documents. The documents are parsed into a machine-readable representation, and data items in the machine-readable representation are identified according to the schema. Interpretations of data items are propagated within the documents to disambiguate identified data items, and identified data items are matched with other data items in the documents according to the schema. Only identified data items that include a minimal set of interpretations specified by the schema are extracted.

Abstract: A method of extracting data from documents is provided. The method comprises receiving input of a number of documents and input of a schema of data items available for extraction from the documents. The documents are parsed into a machine-readable representation, and data items in the machine-readable representation are identified according to the schema. Interpretations of data items are propagated within the documents to disambiguate identified data items, and identified data items are matched with other data items in the documents according to the schema. Only identified data items that include a minimal set of interpretations specified by the schema are extracted.

Abstract: Techniques are provided for compiling source code. A first code portion is generated that corresponds to the source code and is included in an application program. An attribute setting is received indicating an execution environment for the application program. A second code portion included in the application program is conditionally generated in accordance with the attribute setting. A determination is made as to whether the attribute setting is a first value indicating a first execution environment. If the attribute setting is the first value, a deployment manifest file and an application manifest filed are generated. The manifest files are used in connection with installation of the application program for execution in the first execution environment.

Abstract: A method for profiling and identifying persons by using data samples provides a collapsed list of one or more aggregated matching samples having consistent STR profiles. Each of the one or more aggregated matching samples are presented on a one-line display, the one-line display having a composite profile representing consensus of all STR profiles in an associated aggregate matching sample. The one-line display of an aggregated matching sample may be expanded, and the expanded one-line display provides a view of all member samples in the aggregated matching sample. A method for aggregating samples from a plurality of disparate samples, and combining the aggregated samples is also provided.

Abstract: Navigating through pages of content. In aspects, a state machine is provided that simplifies navigating. The state machine allows multiple navigation services to work together in a hierarchical manner to obtain content. The state machine also provides a mechanism for stopping navigation and responding to errors.

Abstract: A method for profiling and identifying persons by using data samples provides a collapsed list of one or more aggregated matching samples having consistent STR profiles. Each of the one or more aggregated matching samples are presented on a one-line display, the one-line display having a composite profile representing consensus of all STR profiles in an associated aggregate matching sample. The one-line display of an aggregated matching sample may be expanded, and the expanded one-line display provides a view of all member samples in the aggregated matching sample. A method for aggregating samples from a plurality of disparate samples, and combining the aggregated samples is also provided.