Abstract: Certain aspects involve training tree-based machine-learning models for computing predicted responses and generating explanatory data for the models. For example, independent variables having relationships with a response variable are identified. Each independent variable corresponds to an action or observation for an entity. The response variable has outcome values associated with the entity. Splitting rules are used to generate the tree-based model, which includes decision trees for determining relationships between independent variables and a predicted response associated with the response variable. The tree-based model is iteratively adjusted to enforce monotonicity with respect to representative response values of the terminal nodes. For instance, one or more decision trees are adjusted such that one or more representative response values are modified and a monotonic relationship exists between each independent variable and the response variable.

Abstract: A blower assembly having a blower housing, an impeller fan within the blower housing, the impeller fan being adapted for rotation about an axis and having a plurality of impeller blades and having an axial length, a motor having a stator and a rotor, the motor having an axial length, the rotor being configured to rotate relative to the stator for rotation about the axis, the rotor and the impeller fan being coupled so that the impeller fan rotates with the rotor about the axis, wherein a ratio of the axial length of the motor to the axial length of the impeller fan is less than 0.3, and a motor support bracket operatively securing the stator to one of the first and second side walls of the blower housing.

Abstract: A blower assembly having a blower housing, an impeller fan within the blower housing, the impeller fan being adapted for rotation about an axis and having a plurality of impeller blades and having an axial length, a motor having a stator and a rotor, the motor having an axial length, the rotor being configured to rotate relative to the stator for rotation about the axis, the rotor and the impeller fan being coupled so that the impeller fan rotates with the rotor about the axis, wherein a ratio of the axial length of the motor to the axial length of the impeller fan is less than 0.3, and a motor support bracket operatively securing the stator to one of the first and second side walls of the blower housing.

Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among the common factors. The adjusted neural network can be used to generate explanatory indicating relationships between (i) changes in the risk indicator and (ii) changes in at least some common factors.

Abstract: In some aspects, a computing system can generate and optimize a neural network for risk assessment. The neural network can be trained to enforce a monotonic relationship between each of the input predictor variables and an output risk indicator. The training of the neural network can involve solving an optimization problem under a monotonic constraint. This constrained optimization problem can be converted to an unconstrained problem by introducing a Lagrangian expression and by introducing a term approximating the monotonic constraint. Additional regularization terms can also be introduced into the optimization problem. The optimized neural network can be used both for accurately determining risk indicators for target entities using predictor variables and determining explanation codes for the predictor variables. Further, the risk indicators can be utilized to control the access by a target entity to an interactive computing environment for accessing services provided by one or more institutions.

Abstract: Certain aspects involve building and debugging models for generating source code executed on data-processing platforms. One example involves receiving an electronic data-processing model, which generates an analytical output from input attributes weighted with respective modeling coefficients. A target data-processing platform is identified that requires bin ranges for the modeling coefficients and reason codes for the input attributes. Bin ranges and reason codes are identified. Modeling code is generated that implements the electronic data-processing model with the bin ranges and the reason codes. The processor outputs source code, which is generated from the modeling code, in a programming language used by the target data-processing platform.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables compliant with certain monotonicity constraints. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among a subset of the predictor variables corresponding to a common factor.

Abstract: A fan blade platform is provided. The fan blade platform may include a wall, a first sidewall extending from the flowpath to a circular member, and a second sidewall extending from the flowpath to the circular member. A stiffening member may also extend from the circular member to the flowpath and be formed integrally with the first sidewall, the second sidewall, and the flowpath.

Abstract: A video item is provided for playback at a media player executing at a user device. The media player is logically divided into multiple sections. An indication of a touch gesture made by a user with respect to a touchscreen of the user device is received. Whether the touch gesture with respect to the touchscreen of the user device qualifies as a first predetermined touch gesture is determined. The first predetermined touch gesture is within a portion of a user interface (UI) that is includes in a first section of the media player. Responsive to determining the touch gesture with respect to the touchscreen of the user device qualifies as the first predetermined gesture, the playback of the video item is moved from a first point in time to a second point in time by a predetermined amount of time.

Abstract: A fan blade includes a tip assembly that is disposed on a blade body. The tip assembly has a leading edge wall disposed proximate a leading edge of the blade body, a trailing edge wall disposed proximate a trailing edge of the blade body, a suction side wall that extends between the leading edge wall and the trailing edge wall, a pressure side wall disposed opposite the suction side wall and extends between the leading edge wall and the trailing edge wall, and a tip wall that extends between the leading edge wall, the trailing edge wall, the suction side wall, and the pressure side wall and is disposed parallel to the tip.

Abstract: Certain aspects involve building and debugging models for generating source code executed on data-processing platforms. A target data-processing platform is identified that requires bin ranges for modeling coefficients and reason codes for input attributes. A processor outputs source code, which is generated from a modeling code, in a programming language used by the target data-processing platform.

Abstract: Certain aspects involve optimizing neural networks or other models for assessing risks and generating explanatory data regarding predictor variables used in the model. In one example, a system identifies predictor variables compliant with certain monotonicity constraints. The system generates a neural network for determining a relationship between each predictor variable and a risk indicator. The system performs a factor analysis on the predictor variables to determine common factors. The system iteratively adjusts the neural network so that (i) a monotonic relationship exists between each common factor and the risk indicator and (ii) a respective variance inflation factor for each common factor is sufficiently low. Each variance inflation factor indicates multicollinearity among a subset of the predictor variables corresponding to a common factor.

Abstract: An electric machine comprising a permanent magnet rotor assembly is provided. The electric machine comprises a permanent magnet rotor assembly comprising a plurality of permanent magnets coupled to a rotor disk and a plurality of magnet shims coupled to the plurality of permanent magnets opposite the rotor disk. Each magnet shim of the plurality of magnet shims has a substantially complementary shape as a respective permanent magnet of the plurality of permanent magnets. The electric machine further comprises a stator core comprising a plurality of stator teeth that define a plurality of slots therebetween. At least one of the plurality of magnet shims is configured to direct magnetic flux from at least one of the plurality of permanent magnets to at least one stator tooth of the plurality of stator teeth.

Abstract: In some implementations, a method includes receiving, from a virtual machine, a request to create a proxy agent configured to monitor an application executing on the virtual machine, wherein the proxy agent is associated with the virtual machine and wherein the virtual machine is unable to host the proxy agent. The method also includes creating the proxy agent based on the request to create the proxy agent. The method further includes receiving monitoring data for the application executing on the virtual machine via the proxy agent. The method further includes transmitting a status of the application or the monitoring data to a server.

Abstract: A method of touch gesture control of video playback is discloses. The method includes providing a video item for playback The method also receives an indication of a touch gesture made by a user of mobile user device. The method further determines whether the touch gesture is a swipe gesture within a portion of a user interface (UI) including a media player to play the video item. The method also moves the playback of the video item from a first point in time to a second point in time by a predetermined amount of time in response to determining the touch gesture is the swipe gesture within the portion of the UI comprising the media player.

Abstract: A method comprising: conducting a hearing test for a user over a communication link established between a network entity in a communication network and a user device of a user; wherein the hearing test comprises providing audio stimuli to the user device at a plurality of test frequencies over the communication link, and monitoring responsiveness to the audio stimuli received from the user device; generating a hearing profile based on results of the hearing test; and storing the hearing profile and information associated with the user in a memory of a network entity, such that the hearing profile is available for modifying of audio signals to the user device.

Abstract: A spacer assembly for a rotor assembly of a gas turbine engine includes an endwall segment having a non-axisymmetric flowpath surface, a first depression and a second depression. A perimeter of the flowpath surface includes a forward edge, an aft edge, a suction side edge and a pressure side edge. The first depression is formed along the flowpath surface adjoining the suction side edge, and the second depression is formed along the flowpath surface adjoining the pressure side edge.

Abstract: A system and method for streaming video with dynamic user features enable content distribution systems to increase a user's total watch time. Automated playback and pause modes are disclosed that allow a user to select a preferred playback mode and have that mode persist across sessions and application launches.

Abstract: A blower assembly having a blower housing, an impeller fan within the blower housing, the impeller fan being adapted for rotation about an axis and having a plurality of impeller blades and having an axial length, a motor having a stator and a rotor, the motor having an axial length, the rotor being configured to rotate relative to the stator for rotation about the axis, the rotor and the impeller fan being coupled so that the impeller fan rotates with the rotor about the axis, wherein a ratio of the axial length of the motor to the axial length of the impeller fan is less than 0.3, and a motor support bracket operatively securing the stator to one of the first and second side walls of the blower housing.