A method using a fast algorithm automated analysis of time series sensor data that can find an optimal clustering value k for k-means analysis by using statistical analysis of the results of clustering for a stated maximal upper value of k.

Systems, methods, and non-transitory computer-readable media train a machine learning model to forecast growth of a content item, the growth being measured based at least in part on a count of user interactions with the content item, wherein the model is trained to adjust growth forecasts for the content item in response to one or more users interacting with the content item. A first growth forecast for the content item can be determined for a unit of time using the machine learning model. A determination is made that a first user has interacted with the content item. A second growth forecast for the content item can be determined for the unit of time using the machine learning model and based at least in part on the first user interacting with the content item.

An online system receives a request from a user of the online system to generate a content item specifying content (e.g., an image) received from the user and one or more modifications to the appearance of the content to be included in the content item. The online system generates multiple instances of the content item based on the request, in which each instance includes a different set of the specified modifications. Using an identifier that identifies each instance based on the set of modifications to the appearance of the included content (e.g., using an image fingerprint), the online system tracks a performance metric associated with each instance. By comparing the performance metrics associated with the instances, the online system identifies one or more modifications responsible for one or more differences between the performance metrics and predicts an effect on the performance metrics associated with content item instances including the identified modifications.

Methods, systems, and apparatus for prioritizing communications are described. Metadata that characterizes an electronic communication is obtained and a machine learning algorithm is applied to the metadata to generate a scoring model. A score for the electronic communication is generated based on the scoring model.

A control system and method for controlling a system, which employs a data set representing a plurality of states and associated trajectories of an environment of the system; and which iteratively determines an estimate of an optimal control policy for the system. The iterative process performs the substeps, until convergence, of estimating a long term value for operation at a respective state of the environment over a series of predicted future environmental states; using a complex return of the data set to determine a bound to improve the estimated long term value; and producing an updated estimate of an optimal control policy dependent on the improved estimate of the long term value. The control system may produce an output signal to control the system directly, or output the optimized control policy. The system preferably is a reinforcement learning system which continually improves.

A method for performing program analysis includes receiving programs of a first platform that have been assigned a first label and programs of the first platform that have been assigned a second label. Each of the programs of the first platform is expressed as platform-independent logical features. A discriminatory model or classifier is trained, using machine learning, based on the expression of the programs of the first platform as platform-independent logical features, to distinguish between programs of the first label and programs of the second label. An unlabeled program of a second platform is received and is expressed as platform-independent logical features. The trained discriminatory model or classifier is used to determine if the unlabeled program warrants the first label or the second label, based on the expression of the unlabeled program as platform-independent logical features.

Systems, methods, and non-transitory computer-readable media according to certain aspects can receive at least one message sent by a user of a social networking system to a page provided by the social networking system, where the page is associated with an entity. A training data set including a plurality of messages can be determined, and the training data set can indicate an intent classification for each of the plurality of messages. The intent classification can be indicative of an intent associated with a particular message. A machine learning model may be trained based at least in part on the training data set. A first intent classification for the at least one message can be determined, based at least in part on the machine learning model.

Web security methods and apparatus are disclosed herein. A method includes receiving a detection model for detecting malicious webpages via a transceiver of the computing device, and storing the detection model in a non-volatile memory of the computing device. One or more JavaScripts are detected in the webpage, wherein each of the JavaScripts can be separately executed. A feature vector for each of the JavaScripts may be generated, either incrementally as the web page is being loaded or prefetching the JavaScript for the web page, to produce one or more feature vectors for the webpage, wherein a particular feature vector includes values for different features of a JavaScript. Each of the feature vectors are analyzed with the multi-instance learning based detection model to determine whether the webpage from which the JavaScripts originate is malicious or benign.

Training prediction models and applying machine learning prediction to data is illustrated herein. A prediction instance comprising a set of data and metadata associated with the set of data identifying a prediction type is obtained. The data and metadata are used to determine an entity to train a prediction model using the prediction type. A trained prediction model is obtained from the entity. A notification system may be configured to react to monitor contextual information and apply the prediction. A workflow system may automatically perform a function in a workflow based on prediction.

A method of collaboratively developing software includes recording a plurality of developers' tasks relating to a collection of software development files via software executing on a computer. The method further includes calculating a proximity score between a plurality of tasks based on the overlap of the developers' activities via software executing on a computer. The method further includes selecting and capturing a group of task properties that along with the proximity score can be used to select a group of task pairings that require coordination. The method further includes notifying the developers assigned to the task pairings selected that they may need to coordinate their development efforts.