Abstract: Provided is a system for analyzing features associated with entities using an embedding tree, the system including at least one processor programmed or configured to receive a dataset associated with a plurality of entities, wherein the dataset comprises a plurality of data instances for a plurality of entities. The processor may be programmed or configured to generate at least two embeddings based on the dataset and determine split criteria for partitioning an embedding space of at least one embedding tree associated with the dataset based on feature data associated with an entity and embedding data associated with the at least two embeddings. The processor may be programmed or configured to generate at least one embedding tree having a plurality of nodes based on the split criteria. Methods and computer program products are also provided.

Abstract: A method for calculating traffic flow changes includes detecting a traffic event. The method further includes determining an affected area of the traffic event and determining an investigation area based on the affected area. The method further includes selecting at least one vehicle located within the investigation area and calculating a change in traffic flow due to the traffic event based on a comparison of a predicted traffic flow with a current traffic flow, wherein the current traffic flow is based on information received from the at least one vehicle. The method further includes updating the affected area based on the change in traffic flow and calculating an updated change in traffic flow based on the updated affected area when the updated affected area is larger than a predetermined threshold area.

Abstract: The disclosure provides a system, a method and a computer program product for dynamic scoring of a plurality of incidents. The system is configured to retrieve an incident of the plurality of incidents. The incident comprises at least one alert and is associated with a security breach. The system further generates an enriched alert based on enrichment of the at least one alert. The enrichment is based on security related data of the security breach. The system further identifies one or more entities and one or more observables associated with the generated enriched alert. The system determines a score for the retrieved incident based on at least the generated enriched alert and the generated behavioural entity model. The system is further configured to dynamically update the determined score for the retrieved incident based on an analysis of at least the retrieved incident and the generated behavioural entity model.

Abstract: A data processing system for generating predictive maintenance models is disclosed, including one or more processors, a memory, and a plurality of instructions stored in the memory. The instructions are executable to receive a historical dataset relating to each of a plurality of systems, including maintenance data and operational data. The instructions are further executable to display one or more algorithm templates and one or more data features calculated from the operational data, in a graphical user interface. The instructions are further executable to receive a selection of an algorithm template, a data feature, and a value of a parameter associated with the algorithm template, and to train and evaluate the selected algorithm template on the selected data feature according to the received value. The instructions are further executable to display a result of a metric of the evaluation, and generate a predictive maintenance model using the selected algorithm template.

Abstract: Devices and techniques are generally described for detection of abusive computational nodes. In various examples, first input data describing a first plurality of computational nodes and first data identifying a dimension along which to parse the first plurality of computational nodes may be received. A first computing device may generate input graph data representing the first plurality of computational nodes. The computational nodes of the first plurality of computational nodes may share a same value for the dimension are connected to one another in the input graph data. In various examples, a first graph machine learning model and at least one known abusive computational node may be used to determine a first set of candidate computational nodes for further evaluation. In some cases, network access of a first computational node of the first set of candidate computational nodes may be terminated.

Abstract: A non-transitory computer-readable medium comprising computer-executable instructions that, when executed, are configured to cause a processor to perform operations that include receiving process input data associated with one or more automation devices, determining a plurality of operating conditions corresponding to the one or more automation devices; clustering the process input data based on the plurality of operating conditions, receiving a decision tree representative of the plurality of operating conditions and corresponding process input data, determining a splitting criterion for one or more nodes of the decision tree based on the clustered process input data, wherein the splitting criterion is configured to link the process input data to at least two operating conditions based on the decision tree, generating control logic for the one or more automation devices based on the decision tree and splitting criterion, and sending the control logic to the one or more automation devices.

Abstract: A nuclide identification method, a system and an electronic device are provided, which relates to the field of nuclide identification. According to statistical characteristics, a background probability density function and a Compton probability density function in a ROI are determined. An energy Bayesian factor and a time Bayesian factor are determined based on energy and time interval information in a sequence of the nuclear detection events obtained by measurement. By combining the two factors, Compton plateau can be effectively identified and distinguished.

Abstract: In a search and tracking method for full time-domain laser detection of space debris, a set of latest precision orbital parameters of a debris object and start and end moments of a current transit of the object are first obtained. Search-specific guidance data is generated based on the above information and in combination with estimation of a maximum along-track error of the orbital parameters of the object during the current transit. A DLR system performs multi-elevation search on the object based on the search-specific guidance data, obtains a plurality of pieces of detection data of the object after detecting the object during the search, determines an along-track error of the orbital parameters of the object based on the detection data, and corrects the orbital parameters of the object in real time based on the along-track error, so as to guide the DLR system to subsequently track and detect the object.

Abstract: Systems and methods ingest extensive data regarding real-time transactions to determine correlation between a variety of parameters and possible fraud events. Possible fraud can be predicted, and notifications delivered to a fraud team. Correlations can be discovered using unsupervised machine learning, and particular systems and methods can utilize natural language processing to both receive and provide information concerning fraud risk and countermeasures.

Abstract: A system creates a mapping of a storage intent, defined for a digital asset, to one of the primary storage tiers, in a primary protection storage system, which matches the storage intent. The system receives a request to store a copy of the digital asset and stores the copy with the storage intent in the primary storage tier, based on the mapping of the storage intent to the primary storage tier. Upon receiving a request to replicate the copy of the digital asset, the system creates a mapping of the storage intent to one of the secondary storage tiers, in a secondary protection storage system, which matches the storage intent. The system replicates each copy of the digital asset, which is stored in the primary storage tier, and the storage intent to the secondary storage tier, based on the mapping of the storage intent to the secondary storage tier.

Abstract: A computer implemented method and a system for facilitating modifying environments based on user preferences is provided. Accordingly, the method may include receiving, using a communication device, interaction data of interactions of a user in relation to experiential environments of two or more experiential environments from user devices. Further, the computer implemented method may include analyzing, using a processing device, the interaction data. Further, the computer implemented method may include determining, using the processing device, two or more user preferences associated with the user based on the analyzing of the interaction data. Further, the computer implemented method may include provisioning, using the processing device, two or more content corresponding to the two or more experiential environments based on the two or more user preferences. Further, the computer implemented method may include storing, using a storage device, the interaction data and the two or more user preferences.

Abstract: In a first device, a local classification and a local classification confidence score corresponding to an event input are computed. At the first device in response to a broadcast request, a remote classification and a remote classification confidence score corresponding to the event input are received, the remote classification and the remote classification confidence score being computed at a second device. At the first device, a consensus classification including the most frequent classification from a set of all received remote classifications and the local classification is formed, provided the number of classifications including the most frequent classification exceeds a threshold. In response to a consensus classification confidence score corresponding to the consensus classification exceeding a confidence threshold, a local classification model is updated. Based on the local classification and the consensus classification, the event input is assigned to a classification.

Abstract: An interface and improved data intake and query system is described herein that allows users to define metrics and that aggregates metric values regardless of the level at which a metric is defined and/or the level at which metric values are available. The improved data intake and query system can initialize a sketch in response to a user providing one or more metric definitions. The initialized sketch includes one or more instances, where each instance produces an output and collects metric value(s), appends the metric value(s) to the output, and forwards the appended data to a process function downstream in a data processing pipeline. The process function separates the output and the metric value(s), sending the output further downstream in the data processing pipeline and sending the metric value(s) to a parallel process function that sits outside the data processing pipeline. The parallel process function can persist the metric value(s).

Abstract: A method of providing a video stream based on machine learning in an electronic device according to various example embodiments may include receiving a source video stream which is streamed from a first device to at least one other device, confirming whether an event is detected on the source video stream using a learning model trained through machine learning on the basis of at least one frame of the source video stream, and determining whether to restrict streaming of the source video stream from the first device on the basis of the event detection. In addition to the method, other example embodiments are possible.

Abstract: The present disclosure provides systems and methods that leverage machine-learned models in conjunction with user-associated data and disease prevalence mapping to predict disease infections with improved user privacy. In one example, a computer-implemented method can include obtaining, by a user computing device associated with a user, a machine-learned prediction model configured to predict a probability that the user may be infected with a disease based at least in part on user-associated data associated with the user. The method can further include receiving, by the user computing device, the user-associated data associated with the user. The method can further include providing, by the user computing device, the user-associated data as input to the machine-learned prediction model, the machine-learned prediction model being implemented on the user computing device.

Abstract: A clinical diagnostic analyzer for performing a virtual crossover study on quality control (QC) material includes a processor, memory, measurement hardware, and an input panel/display. The analyzer acquires data from a peer group relating to a new lot of quality control material to calculate a predicted mean and standard deviation based on that peer group data and adjusted for bias in the laboratory process. As new analyses are run on the new lot of QC material, the predicted mean and standard deviation are updated to incorporate the actual data on a weighted basis.

Abstract: Systems and methods are described for selecting content item identifiers for display. The system may identify a set of content items that are likely to be requested in the future based on a history of content item requests. The system then selects a first plurality of content categories using a category selection neural net and selects a first set of recommended content items for the first plurality of content categories. The system increases a reward score for the first plurality of content categories based on receiving a request for a content item that is included in the first set of recommended content items. The system also decreases the reward score for the first plurality of content categories based on determining that the requested content item is included in the set of content items that are likely to be requested in the future. The neural net is trained based on the reward score of the first plurality of content categories to reinforce reward score maximization.

Abstract: Provided are a data processing method and apparatus, an electronic device, and a medium, and relates to the technical field of computers, and in particular to the field of autonomous driving and intelligent transportation. An implementation is: obtaining risk information in driving scenario data of a driving scenario; determining a risk factor set based on the risk information, where the risk factor set includes a risk factor existing in the driving scenario data; and generating a simulated risk scenario based on the risk factor set, where the simulated risk scenario reflects at least one risk factor in the risk factor set.

Abstract: A method, apparatus and a product for data generalization for predictive models. The method comprising: obtaining a training dataset that comprises a plurality of training instances and predicted labels thereof, wherein each training instance is a valuation of a set of features, wherein the set of features comprises a feature having a domain, wherein the predicted label of each training instance is a label predicted thereto by a predictive model; training an auxiliary model using the training dataset; based on the auxiliary model, determining an alternative set of features that is a generalization of the set of features, wherein the alternative set of features comprises a generalized feature having a generalized domain, wherein each value in the generalized domain corresponds to one or more values in the domain; obtaining a generalized instance having a valuation of the alternative set of features; and determining a label for the generalized instance.

Abstract: Embodiments of this disclosure include an image processing method and apparatus. The method may include obtaining feature points corresponding to training images and feature center points of images in a second quantity of categories and obtaining a feature condition probability distribution that the feature points collide with corresponding feature center points. The method may further include performing network training to obtain target feature center points of the images in the second quantity of categories. The method may further include mapping the first quantity of feature points and the second quantity of target feature center points to a Hamming space, to obtain hash codes of the first quantity of training images and hash center points of the images in the second quantity of categories. The method may further include performing network training using the hash condition probability distribution and the ideal condition probability distribution, to obtain an image hash model.

Abstract: Described systems and techniques determine causal associations between events that occur within an information technology landscape. Individual situations that are likely to represent active occurrences requiring a response may be identified as causal event clusters, without requiring manual tuning to determine cluster boundaries. Consequently, it is possible to identify root causes, analyze effects, predict future events, and prevent undesired outcomes, even in complicated, dispersed, interconnected systems.

Abstract: Systems, computer-implemented methods, and computer program products to facilitate quantum state preparation of a probability distribution to perform amplitude estimation are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a data loader component that prepares a quantum state of a probability distribution based on structure of a quantum amplitude estimation algorithm. The computer executable components can further comprise an operator component that constructs a quantum operator based on the quantum state to perform quantum amplitude estimation.

Abstract: A control system includes an obtainer that obtains sensing data output from a sensor that performs sensing of an outside of a mobile body, a detector that detects a position of an object outside the mobile body based on the sensing data, a movement predictor that predicts a movement of the object based on the sensing data, a costmap generator that generates a first costmap based on the position detected of the object and a second costmap based on the movement predicted of the object, a path generator that generates a path for the mobile body based on the first costmap, a determination generator that generates a movement determination of the mobile body based on the second costmap and the path generated, and a controller that controls the movement of the mobile body in accordance with the path generated and the movement determination.

Abstract: There is a need for more effective and efficient predictive data analysis based at least in part on categorical input data. This need can be addressed by, for example, solutions for performing predictive data analysis that utilize at least one of categorical level merging, mutual-information-based feature filtering, feature-correlation-based feature filtering to generate training data feature value arrangements, as well as training and using categorical input machine learning models trained using the training data feature value arrangements.

Abstract: A neural network system can select content based on user and item content embeddings in an approach that can be updated in real time on the user device without server support. Requests for content sent to the server can include an anonymous user embedding that includes data describing the user's inputs. The content that is nearest to the user embedding in a joint embedding space can be returned as suggested content.

Abstract: Embodiments of the present disclosure relate to a method, system, and computer program product for efficient execution of a decision tree. According to the method, respective target values of a plurality of attributes of a target entity are obtained. Representations of a plurality of leaf nodes of a decision tree are obtained. Each of the representations indicates respective statistic values of a plurality of attributes of historical entities and a statistic prediction result determined from historical prediction results output at a respective one of the plurality of leaf nodes for the historical entities. Distance measures between the target entity and the plurality of leaf nodes are determined based on the target values and the statistic values indicated by the representations of the plurality of leaf nodes. A target prediction result for the target entity is determined based on the distance measures and the statistic prediction results of the historical entities.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for dialogue systems. A transcription of a user utterance is obtained. The transcription of the utterance is tokenized to identify multiple tokens for the utterance. Token-level utterance encodings corresponding to different tokens of the transcription are generated. A system action encoding from data indicating system actions previously performed by the dialogue system are generated. A dialogue context vector based on the utterance encoding and the system action encoding are generated. The token-level utterance encodings, the system action encoding, and the dialogue context vector are processed using a slot tagger to produce token-level output vectors. A limited set of candidate token classifications for the tokens of the user utterance are determined based on the token-level utterance encodings. A response for output is provided in response to the user utterance.

Abstract: An intention identification model learning method includes receiving positive data that corresponds to a first skill, generating, based on the positive data that corresponds to the first skill, negative data that corresponds to the first skill, determining a second skill similar to the first skill, obtaining data that corresponds to each second skill, generating a second base model based on the data that corresponds to the second skill and a first base model stored on the server, and performing learning based on the second base model, the positive data, and the negative data that correspond to the first skill, and generating an intention identification model.

Abstract: In various examples, the present disclosure relates to using temporal filters for automated real-time classification. The technology described herein improves the performance of a multiclass classifier that may be used to classify a temporal sequence of input signals—such as input signals representative of video frames. A performance improvement may be achieved, at least in part, by applying a temporal filter to an output of the multiclass classifier. For example, the temporal filter may leverage classifications associated with preceding input signals to improve the final classification given to a subsequent signal. In some embodiments, the temporal filter may also use data from a confusion matrix to correct for the probable occurrence of certain types of classification errors. The temporal filter may be a linear filter, a nonlinear filter, an adaptive filter, and/or a statistical filter.

Abstract: The present disclosure relates to improving recommendations for small shops on an ecommerce platform while maintaining accuracy for larger shops by retraining a machine-learning recommendation model to reduce sample selection bias using a meta-learning process. The retraining process comprises identifying a sample subset of shops on the ecommerce platform, and then creating shop-specific versions of the recommendation model for each of the shops in the subset by optimizing the baseline model to predict user-item interactions in a first training dataset for the applicable shop. Each of the shop-specific models is then tested using a second training dataset for the shop. A loss is calculated for each shop-specific model based on the model's predicted user-item interactions and the actual user-item interactions in the second training dataset for the shop. A global loss is calculated based on each of the shop-specific losses, and the baseline model is updated to minimize the global loss.

Abstract: A course prediction device (1) includes a blind spot calculation unit (11) and a prediction unit (12). The blind spot calculation unit (11) acquires a sensing result sequentially from a sensor which is arranged in a mobile object and which detects whether an object exists, and calculates, based on sensor information, a blind spot area expressing such an area that an object existing therein cannot be detected by the sensor. The blind spot calculation unit (11) also detects an object entering the blind spot area based on the sensor information. The prediction unit (12) predicts a course in the blind spot area of the detected object based on the sensing result.

Abstract: An audio processing method by which input data are obtained that includes first sound data representing first components of a first frequency band, included in a first sound corresponding to a first sound source, second sound data representing second components of the first frequency band, included in a second sound corresponding to a second sound source, and mix sound data representing mix components of an input frequency band including a second frequency band, the mix components being included in a mix sound of the first sound and the second sound. The input data are then input to a trained estimation model, to generate at least one of first output data representing first estimated components within an output frequency band including the second frequency band, included in the first sound, or second output data representing second estimated components within the output frequency band, included in the second sound.

Abstract: One example method of operation may include identifying a content thread in a content sharing forum, assigning a bot to process messages of the content thread, identifying, via the bot, a question message, parsing the question message content to identify topics of interest, processing the messages of the content thread to identify response information related to the question message, determining the response information to the question message requires third party information, and transmitting a request, with the question message content, to one or more other bots operating in other content sharing forums.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a backward looking surprise metric for autonomously driven vehicles. One of the methods includes obtaining first data representing one or more previously predicted states of an agent along one or more predicted trajectories of the agent at a first time step. Second data representing one or more states of the agent at a subsequent time step is obtained. A surprise score is computed from a measure of a difference between the first data computed for the one or more predicted trajectories for the prior time step and the second data computed for the one or more predicted states for the subsequent time step.

Abstract: A computing device, method, and system are provided of improving data quality to conserve computational resources. The computing device receives a raw dataset. One or more data quality metric goals corresponding to the received raw dataset are received. A schema of the dataset is determined. An initial set of validation nodes is identified based on the schema of the dataset. The initial set of validation nodes are executed. A next set of validation nodes are iteratively expanded and executed based on the schema of the dataset until a termination criterion is reached. A corrected dataset of the raw dataset is provided based on the iterative execution of the initial and next set of validation nodes.

Abstract: Techniques for implementing Bayesian model for refining and petrochemical wall thickness monitoring are presented. The construction of a model may be automated for each piping circuit or piece of major fixed equipment, utilizing, for example, specific component data, historical thickness measurements, inspection practices and related inspection program information. The model contains nodes describing the most significant sources of variability, namely component original thicknesses, wall thickness degradation over time, corrosion rates and thickness measurement error.

Abstract: Various embodiments include systems and methods to implement a security platform providing cyberattack detection. The security platform may, with respect to a cloud compute environment, use audit log data that is associated with a particular domain of operational activity within the cloud compute environment. Based on a domain specific graph representative of factor data and dependencies between factor data, the security platform may determine a behavioral anomaly that is associated with a cyberattack.

Abstract: A computerized method for detection of categorical drift within an incoming data stream. Herein, an error threshold is computed based on a first set of training data samples selected to detect categorical drift occurring for a data stream. Thereafter, probability distributions associated with content of a first and second data samples of the data stream are computed. Analytics are conducted to compute a difference between content of the first probability distribution that is based on a first data point of the first data sample and content of the second probability distribution that is based on a first data point of the second data sample. After computing the difference, that categorical drift is determined whether categorical drift detection has been conducted.

Abstract: A machine learning algorithm is trained on a number of microscopic images and a measure of outcome of each image. Each image is divided into tiles. The measure of outcome is assigned to each tile of the image. The tiles are then used to train the machine learning algorithm. The trained algorithm may then be used to evaluate images.

Abstract: Systems and methods are provided for authorizing an electronic transaction. In one implementation at least one processor is programmed to receive electronic transaction data and historical transaction data, the electronic transaction data including an entity identifier component and an amount component of an electronic transaction; determine, based on the entity identifier component and the amount component, a location of the electronic transaction in a space of a distributed representation space, the distributed representation space comprising a mapping of electronic transaction components in a high-order space; determine locations of the historical transaction data in the distributed representation space; determine a decision boundary in the distributed representation space based on the locations of the historical transaction data; and authorize the electronic transaction based on the location of the electronic transaction being within the decision boundary.

Abstract: In one example of the technology, device information associated with a device upgrade and a plurality of devices includes risk parameters including values associated with a minimum health value that is associated with a minimum acceptable number of healthy devices among the plurality of devices and a confidence value associated with a minimum acceptable probability that the number of healthy devices among the plurality of devices is at least as great as the minimum health value; and, for each device a success probability value that is associated with a probability that the device will be healthy after the device upgrade is performed on the device. A Poisson binomial distribution is iteratively used to determine a set of devices among the plurality of device for which the largest possible number of devices are included in the set of devices while meeting the risk parameters. The set of devices is then upgraded.

Abstract: A method for discovering causality from data includes acquiring to-be-processed data, and obtaining a covariance matrix of the to-be-processed data; determining a first target column in the covariance matrix, taking the number of columns of the first target column as a first place in a rearrangement sequence, and obtaining a first upper triangular matrix according to the first target column; determining a position of the number of columns of the covariance matrix other than the first target column except the first place in the rearrangement sequence according to the first target column and the first upper triangular matrix, and obtaining an upper triangular matrix in each position determination; obtaining an adjacency matrix according to an upper triangular matrix and a rearrangement sequence obtained in final position determination; and generating directed acyclic graph (DAG) by using the adjacency matrix, and taking the DAG as causality discovery result of the to-be-processed data.

Abstract: An urban design pipeline automatically generates design options for an urban design project. The urban design pipeline includes a geometry engine and an evaluation engine. The geometry engine analyzes design criteria, design objectives, and design heuristics associated with the urban design project and then generates numerous candidate designs. The design criteria specify a property boundary associated with a region of land to be developed. The design objectives indicate a specific type of topology that is derived from an existing urban layout. The design heuristics include different sets of construction rules for generating designs with specific types of topologies. The geometry engine generates candidate designs that conform to the property boundary and have topological characteristics in common with the existing urban layout.

Abstract: Sound source enhancement technology is provided that is capable of improving sound source enhancement capabilities in accordance with settings of usage and applications. A PSD optimization device includes a PSD updating unit that takes a target sound PSD input value {circumflex over (?)}?S(?, ?), an interference noise PSD input value {circumflex over (?)}?IN(?, ?), and a background noise PSD input value {circumflex over (?)}?BN(?, ?) as input, and generates a target sound PSD output value ?S(?, ?), an interference noise PSD output value {circumflex over (?)}?IN(?, ?), and a background noise PSD output value {circumflex over (?)}?BN(?, ?), by solving an optimization problem for a cost function relating to a variable uS representing a target sound PSD, a variable uIN representing an interference noise PSD, and a variable uBN representing a background noise PSD.

Abstract: An association metric for record attributes associated with cardinalities that are not necessarily the same is used for training and/or applying an entity resolution (ER) model. A pair of records includes (a) a first record indicating a first set of values for a first attribute and (b) a second record indicating a second set of values for a second attribute. Each of the first set of values and each of the second set of values are compared to determine individual association metrics. A first-level reduction operation is applied to subsets of the individual association metrics to determine reduced association metrics. A second-level reduction operation is applied to the reduced association metrics to determine an association metric, for the pair of records, for training and/or applying an ER model.

Abstract: Techniques are described herein for collaborative search sessions through an automated assistant. A method includes: receiving, from a first user of a first client device, a first query in a query session; providing, to the first user, a first set of search results; determining, based on at least one term in the first query, that the first query is relevant to a second user of the first client device; providing, to the second user, a selectable option to join the query session; in response to receiving, from the second user, an indication of acceptance of the selectable option, adding the second user to the query session; receiving, from the second user, additional input; generating, based on the additional input received from the second user, a modified set of search results; and providing, to the first user and the second user, the modified set of search results.

Abstract: Computerized methods and systems, including computer programs encoded on a computer storage medium, may adaptively predict expression of emotions based on collected biometric data. For example, a computing system may receive first data indicative of a first time-evolving movement of a portion of a body during a collection period, and may obtain second data identifying predictive models that correlate default emotions with second feature values that characterize body movements during prior collection periods. Based on an outcome of the application of the least one pattern recognition algorithm or machine learning algorithm to portions of the first and second data, the system may determine a corresponding one of the default emotions represented by the first time-evolving movement, and may transmit data indicative of the corresponding one of the default emotions to the communications device for presentation to a user.

Abstract: A client device processing received emoji messages using emoji-first messaging. Text messaging is automatically converted to emojis by an emoji-first application so that only emojis are communicated from one client device to another client device. Each client device has a library of emojis that are mapped to words, which libraries are customizable and unique to the users of the client devices, such that the users can communicate secretly in code. Upon receipt of a string of emojis, a user can select the emoji string to convert to text if desired, for a predetermined period of time.

Abstract: A method of generating a multi-modal prediction is disclosed herein. A computing system retrieves event data from a data store. The event data includes information for a plurality of events across a plurality of seasons. Computing system generates a predictive model using a mixture density network, by generating an input vector from the event data learning, by the mixture density network, a plurality of values associated with a next play following each play in the event data. The mixture density network is trained to output the plurality of values near simultaneously. Computing system receives a set of event data directed to an event in a match. The set of event data includes information directed to at least playing surface position and current score. Computing system generates, via the predictive model, a plurality of values associated with a next event following the event based on the set of event data.

Abstract: A method includes identifying, by pre-set criteria, a first plurality of optical channels and a second plurality of optical channels using optical data generated from a plurality of optical filters of a tester tool. The method also includes determining, from the optical data, a first plurality of fluid types detected by each channel in the first plurality of optical channels using a bootstrap fluid identification technique and determining, from the optical data and the first plurality of fluid types, a second plurality of fluid types detected by each channel in the second plurality of optical channels using a guided fluid identification technique. Further, the method includes generating a spectral signature indicating fluid types for each channel within the tester tool based on the first plurality of fluid types and second plurality of fluid types.