Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations thereof, for stochastic multi-period multi-objective optimization based recommendation system. An embodiment assigns a respective plurality of stochastic parameters to a plurality of recommendation objectives. The embodiment further associates each program of a plurality of programs with one or more recommendation objectives of the plurality of recommendation objectives, and selects, during a first recommendation time period, a first set of operative recommendation objectives from the plurality of recommendation objectives based on the plurality of stochastic parameters. The embodiment then generates a first ordered list of recommended programs from the plurality of programs based on the first set of operative recommendation objectives.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for reducing active user or active content category bias in content recommendation systems. An example embodiment operates by modifying a streaming event data set by selecting a voting algorithm. The voting algorithm reduces an impact of highly occurring data points by sampling the streaming event data set to generate a sampled streaming event data set, wherein the highly occurring data points comprise data points generated by the active users or the active content categories. The embodiment further trains, by a machine learning engine and based on the sampled streaming event data set, a machine learning model to generate a reduced bias content recommendation model and generates, based on the reduced bias content recommendation model, content recommendations for subsequent selection and rendering on a media device.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method, and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for demographic predictions for content items. An example embodiment operates by assigning weights representing demographics to a first plurality of nodes of a predictive model and assigning predictive values representing predicted demographics to a second plurality of nodes of the model. Pairwise distances between the predictive values for the nodes of the second plurality of nodes and the weighted values of the first plurality of nodes may be calculated and the shortest calculated pairwise distances may be used to assign demographics for content items corresponding to nodes of the first plurality of nodes to content items corresponding nodes of the second plurality of nodes. When content is requested, a content item for which the same demographic has been assigned may be recommended to the requestor.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating trailers (previews) for multimedia content. An example aspect operates by generating an initial set of candidate points to generate a trailer for a media content; determining conversion data for each of the initial set of candidate points; determining an updated set of candidate points based on the conversion data; determining an estimated mean and upper bound for each of the updated set of candidate points; computing a value for each of the updated set of candidate points; generating a ranked list based on the value computed for each of the updated set of candidate points; and repeating the process until an optimal candidate point is converged upon.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for recommending content items. For example, a first content item unassociated with interaction-based data is determined. A description-based representation of the first content item, an image-based representation of the first content item, and/or a metadata-based representation of the first content item is obtained from machine learning model(s). Such representation(s) are provided as an input to a neural network. A first interaction-based representation of the first content item based on such representation(s) is received as an output from the neural network. A measure of similarity is determined between the first interaction-based representation and second interaction-based representation(s) of second content item(s).

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for determining an optimal supplemental content for a media stream menu interface to maximize the consumption of the media stream content by users. An example embodiment operates by performing automated content recognition (ACR) on the media stream, thereby determining optimal supplemental content. The embodiment identifies a plurality of potential supplemental content items in the media stream based on the characteristics of the media stream. The embodiment then outputs the optimal supplemental content to a plurality of predetermined media devices.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for utilizing a content acquisition recommendation system to generating a set of candidate content assets, generate embeddings and popularity score estimates for the set of candidate content assets, aggregate the set of candidate content assets with a set of existing content assets to generate a simulation set of content assets, determine a target set of users for the simulation set of content assets, generate, for at least a portion of the target set of users and based on a trained machine learning model, a result set of recommended content assets, determining an impact of the candidate content assets located in the result set of recommended content assets and generate a proposal for an acquisition of candidate content assets.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating short-form content. An example aspect operates by analyzing a media file in a library using a machine learning model. To analyze the media file, the embodiment determines, using the machine learning model, a first portion of the media file that has a feature that satisfies a classification that the machine learning model is configured to identify. The embodiment tags the first portion using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file. The embodiment then generates a segment from the media file based on the one or more position tags. The segment comprises the portion of the media file and excludes one or more second portions of the media file.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for reducing active user or active content category bias in content recommendation systems. An example embodiment operates by modifying a streaming event data set by selecting a voting algorithm. The voting algorithm reduces an impact of highly occurring data points by sampling the streaming event data set to generate a sampled streaming event data set, wherein the highly occurring data points comprise data points generated by the active users or the active content categories. The embodiment further trains, by a machine learning engine and based on the sampled streaming event data set, a machine learning model to generate a reduced bias content recommendation model and generates, based on the reduced bias content recommendation model, content recommendations for subsequent selection and rendering on a media device.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for recommending content items. For example, a first content item unassociated with interaction-based data is determined. A description-based representation of the first content item, an image-based representation of the first content item, and/or a metadata-based representation of the first content item is obtained from machine learning model(s). Such representation(s) are provided as an input to a neural network. A first interaction-based representation of the first content item based on such representation(s) is received as an output from the neural network. A measure of similarity is determined between the first interaction-based representation and second interaction-based representation(s) of second content item(s).

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for providing content to a user so as to balance known content of interest to the user, and potential new content of interest (e.g., exploration content). An example embodiment operates by receiving and analyzing behavioral data of a user as it relates to exploration content. This behavioral data may include the user selecting, slowing scrolling, pausing scrolling, or other actions that indicate interest in provided exploration content. Based on this data, the user's proclivity for exploration content is determined. This proclivity is compared to a current exploration value associated with the user, and used in one of a variety of different ways to calculate an adjustment to the user's exploration content value, which dictates an amount of exploration content that will be provided to the user.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations thereof, for training a conversational recommendation system. An embodiment generates a pseudo-user neural network model based a pseudo-user profile. The embodiment trains, using the pseudo-user neural network model, the conversational recommendation system to learn a recommendation policy, where the conversational recommendation system includes an interest-exploration engine and a prompt-decision engine. The training includes performing an iterative learning process that includes selecting an interest-exploration strategy and an interest prompt based on an estimated state of the pseudo-user neural network model. The embodiment then generates, using the trained conversational recommendation system, a real-time recommendation having high play probability based on the minimal number of iterations of conversation between a user and the trained conversational recommendation system.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for pairwise comparison rating to reduce presentation bias in content recommendation. An embodiment operates by generating respective ranking values for a plurality of content items based on interactions between user devices and the content items. The respective ranking value for each content item is adjusted based on additional interactions between the user devices and the content items compared to predicted interactions between the user devices and content items. When a first user device of the plurality of user devices requests content, pairwise distances between the respective ranking values for the content items and respective weighted values for historical content items that have been previously interacted with by the first user device are determined.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating short-form content. An example aspect operates by analyzing a media file in a library using a machine learning model. To analyze the media file, the embodiment determines, using the machine learning model, a first portion of the media file that has a feature that satisfies a classification that the machine learning model is configured to identify. The embodiment tags the first portion using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file. The embodiment then generates a segment from the media file based on the one or more position tags. The segment comprises the portion of the media file and excludes one or more second portions of the media file.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for generating a recommendation for a media content of a first form of content based on user interactions with a second form of content. The first form of content is of a different length than the second form of content. An example embodiment operates by determining interaction based data associated with a second form of content based on a user interaction with a first media content. The interaction based data are provided to a machine learning model along with historical data indicative of a user behavior with media contents of the first form or the second form of contents, and metadata associated with the first media content. The machine learning model outputs a second media content of the first form.

Abstract: A set of content items can be accessed by a community of users having a set of interests. A set of interest based clusters for the set of content items correspond to the set of interests. A recommendation system can generate similarity scores for pairs of content items selected from a set of available content items based on metadata associated with the content items. The recommendation system can then generate a set of interest based clusters for the set of content items based on the similarity scores. The recommendation system can determine for a user a group of user interest clusters selected from the set of interest based clusters. Recommendation candidates for the user can be selected for the user from among content items in the group of user interest clusters and can be presented via a user interface.

Abstract: A set of content items can be accessed by a community of users having a set of interests. A set of interest based clusters for the set of content items correspond to the set of interests. For a user, a recommendation system can determine a group of user interest clusters selected from the set of interest based clusters. A popularity score for each content item of the set of content items with respect to the community of users can be generated, and an interest based popularity score for a content item within the interest based cluster can be generated based on a rank of the content item based on the popularity score of the content item. Recommendation candidates for the user can be generated based on the interest based popularity score of the content item for each content item in the group of user interest clusters.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for deep video understanding with large language models. An example embodiment operates by determining a relationship between respective first and second visual elements for each of a plurality of frames of a content item based on respective element types and respective locations for the respective first and second visual elements. For each of the plurality of frames, a respective visual prompt is generated describing the relationship between the respective first and second visual elements. Based on an audio-to-text conversion of audio content associated with the frame or classification of aural elements of the audio content, a respective audio prompt describing the audio content associated with each frame is generated.

Abstract: Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product aspects, and/or combinations and sub-combinations thereof, for generating short-form content. An example aspect operates by analyzing a media file in a library using a machine learning model. To analyze the media file, the embodiment determines, using the machine learning model, a first portion of the media file that has a feature that satisfies a classification that the machine learning model is configured to identify. The embodiment tags the first portion using one or more position tags indicative of a beginning of the first portion of the media file or an end of the first portion of the media file. The embodiment then generates a segment from the media file based on the one or more position tags. The segment comprises the portion of the media file and excludes one or more second portions of the media file.

Abstract: Disclosed herein are system, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for recommending content items. For example, a first content item unassociated with interaction-based data is determined. A description-based representation of the first content item, an image-based representation of the first content item, and/or a metadata-based representation of the first content item is obtained from machine learning model(s). Such representation(s) are provided as an input to a neural network. A first interaction-based representation of the first content item based on such representation(s) is received as an output from the neural network. A measure of similarity is determined between the first interaction-based representation and second interaction-based representation(s) of second content item(s).