Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

Abstract: A method may include determining a combination of values of attributes represented by reference data associated with payment transaction by training a machine learning model based on an association between (i) respective values of the attributes and (ii) the payment transactions having a given result. The combination may be correlated with having the given result. The method may also include selecting a subset of the payment transactions that is associated with the combination of values. The method may additionally include determining a first rate at which payment transactions of the subset have the given result during a first time period and a second rate at which one or more payment transactions associated with the combination have the given result during a second time period, and generating an indication that the two rates differ.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

Abstract: A method may include determining a combination of values of attributes represented by reference data associated with computing devices by training a machine learning model based on an association between (i) respective values of the attributes and (ii) the computing devices entering a device state. The combination may be correlated with entry into the device state. The method may also include selecting a subset of the computing devices that is associated with the combination of values. The method may additionally include determining a first rate at which computing devices of the subset have entered the device state during a first time period and a second rate at which one or more computing devices associated with the combination have entered the device state during a second time period, and generating an indication that the two rates differ.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for modifying one or more parameters of a data streaming bitrate selection algorithm based on machine learning. An example embodiment operates by training and operating a first machine learning model to predict a sustainable network bandwidth. A second machine learning model is trained to receive the sustainable network bandwidth and predict a likelihood that this network bandwidth will not empty a data buffer of streaming data. A bitrate is selected based on the likelihood being below a threshold percentage, such as 50%.

Abstract: Described herein are various embodiments for intelligent advertisement generation and distribution. An embodiment operates by determining website history information about a plurality of consumers and an ad history information about the plurality of consumers. The advertisement is provided for display on a computing device for each consumer of at least a subset of consumers of the plurality of consumers responsive to a first bid opportunity for the advertisement to be displayed. Website actions of the subset of consumers to whom the advertisement was provided for display are tracked. A predictive model that the bid opportunity lead to a conversion is generated based on the website history, ad history, and the tracking of website actions. A price to bid for a second bid opportunity is generated. The generated price to bid is submitted for the second bid opportunity to display the advertisement to a marketplace.

Abstract: The presented technology is directed to devices, systems, and their methods of use for evaluating and optimizing the effectiveness of digital advertisements to increase sales such as in a digital ad-buying platform. In particular, the presented platform is configured for determining incremental lift of a product due to an advertisement and/or a promotion that is distributed online. Presented herein, therefore, are devices, systems, and methods of monitoring, measuring, and/or optimizing lift of an advertising campaign, such as a real-time, digital ad buying campaign implemented by a suitably configured advertising platform.

Abstract: The presented technology is directed to devices, systems, and their methods of use for evaluating and optimizing the effectiveness of digital advertisements to increase sales such as in a digital ad-buying platform. In particular, the presented platform is configured for determining incremental lift of a product due to an advertisement and/or a promotion that is distributed online. Presented herein, therefore, are devices, systems, and methods of monitoring, measuring, and/or optimizing lift of an advertising campaign, such as a real-time, digital ad buying campaign implemented by a suitably configured advertising platform.

Abstract: A decision dashboard system to balance competing objectives in a control system suggests control parameter settings for the control system based on specified weights for the competing objectives. For example, given a target amount of energy consumption for a campus-wide, heating, ventilation, and air conditioning (HVAC) control system, providing an optimal amount of climate control to the different campus locations may compete against the length of time climate control is provided to each of the locations. In some aspects, sets of control system settings may be used to predict outcomes based on a history of control parameter settings and measurements from the control system. In further aspects, the predicted outcomes and their associated control parameter settings may be mapped to different weights for the competing objectives and displayed in a graphical user interface.

Abstract: A decision dashboard system to balance competing objectives in a control system suggests control parameter settings for the control system based on specified weights for the competing objectives. For example, given a target amount of energy consumption for a campus-wide, heating, ventilation, and air conditioning (HVAC) control system, providing an optimal amount of climate control to the different campus locations may compete against the length of time climate control is provided to each of the locations. In some aspects, sets of control system settings may be used to predict outcomes based on a history of control parameter settings and measurements from the control system. In further aspects, the predicted outcomes and their associated control parameter settings may be mapped to different weights for the competing objectives and displayed in a graphical user interface.

Abstract: The invention provides a method and apparatus for automatically generating a summary or key phrase for a song. The song, or a portion thereof, is digitized and converted into a sequence of feature vectors, such mel-frequency cepstral coefficients (MFCCs). The feature vectors are then processed in order decipher the song's structure. Those sections that correspond to different structural elements are then marked with corresponding labels. Once the song is labeled, various heuristics are applied to select a key phrase corresponding to the song's summary. For example, the system may identify the label that appears most frequently within the song, and then select the longest duration of that label as the summary.