Abstract: Computer vision and deep learning techniques are leveraged to detect behavior patterns in transaction histories. A transaction timeline is built for a series of transactions, e.g., financial, and a graphic image is constructed representing the transaction timeline. The graphic image is then matched to a known behavior pattern using a cognitive system. The cognitive system is trained with historical timeline images having associated labels. In one example the graphic image is a bar chart and each financial transaction is represented as a bar in the bar chart having a height proportional to a transaction amount, the bar being located along a time axis of the bar chart according to the transaction date and being color coded according to the transaction type.

Abstract: A semantic, machine readable language part that supports the specification of features is used by an engine that interprets that language to produce the features based on the raw data. In this way, the model developer can specify the measurement columns (for example, data fields), to obtain the dimensions from which the engine can compute the multiple combinations of features possible based on this set of input fields. This computation of features can be used to perform machine learning (ML) training and/or scoring algorithms (for example, ML algorithms for fraud detection).

Abstract: In an approach for optimizing an open feature library, a processor identifies redundancy among a set of features, the set of features previously executed in a machine learning model. A processor performs a predecessor evaluation, the predecessor evaluation including recognizing a feature in the set of features being executed and analyzing an impact of making an upstream feature configuration change relating to the feature. A processor performs a successor evaluation, the successor evaluation including recognizing the feature in the set of features being executed and analyzing an impact of making a downstream feature configuration change relating to the feature. A processor rates the feature against a goal, the goal including overall execution time and overall execution footprint in the machine learning model. A processor updates a state of the feature based on the predecessor evaluation, the successor evaluation, and the feature rating.

Abstract: In an approach for managing an open feature library, a processor collects feature metadata from a data source, the feature metadata being data related to features for training a machine learning model. A processor builds a feature pipeline for the features based on the collected feature metadata. The feature pipeline may be a set of defined and active features. A processor executes the feature pipeline including computing the features. A processor executes a machine learning model using the computed features. A processor evaluates the features and corresponding model results.

Abstract: Computer vision and deep learning techniques are leveraged to detect behavior patterns in transaction histories. A transaction timeline is built for a series of transactions, e.g., financial, and a graphic image is constructed representing the transaction timeline. The graphic image is then matched to a known behavior pattern using a cognitive system. The cognitive system is trained with historical timeline images having associated labels. In one example the graphic image is a bar chart and each financial transaction is represented as a bar in the bar chart having a height proportional to a transaction amount, the bar being located along a time axis of the bar chart according to the transaction date and being color coded according to the transaction type.

Abstract: An automated method and system generates a specification or construction of a building based upon a floor plan, and using modular elements selected from a predetermined set of modular element types. Computer-readable input data representative of a user-generated floor plan is received, which is made up of modular elements arranged in accordance with a regular grid. The input data is processed to produce computer-readable specification data which includes a specification for construction of a building from the modular elements, in accordance with the floor plan. At least one output file is generated, which includes information for use in construction of a building in accordance with the building specification data. The invention enables the design of modular building structures, which can be deployed relatively rapidly and cheaply, by users having no particular skills in building design and/or structural engineering.

Abstract: An elastomeric blocker adapted to be inserted between the adjacent surfaces of a front seat of an automobile and a central console of an automobile to block the gap between the seat and the console and prevent articles from accumulating in the gap. The block has a central slit extending between its top and the bottom aligned longitudinally for the reception of the side seatbelt. A smooth sheet surface coating of fabric or plastic is attached to the section of the elastomer which contacts the central console, so that the blocker slides with the seat as it moves forwardly and rearwardly.

Abstract: An elastomeric blocker adapted to be inserted between the adjacent surfaces of a front seat of an automobile and a central console of an automobile to block the gap between the seat and the console and prevent articles from accumulating in the gap. The block has a central slit extending between its top and the bottom aligned longitudinally for the reception of the side seatbelt. A smooth sheet surface coating of fabric or plastic is attached to the section of the elastomer which contacts the central console, so that the blocker slides with the seat as it moves forwardly and rearwardly.