Patents

Patents, issued:

- Kourosh Modarresi, “Establishing and Utilizing Behavioral Data Thresholds for Deep Learning and Other Models to Identify Users Across Digital Space”, Patent number: 10511681, issued on 12/17/2019.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for providing customized digital content to a client device of a target user by generating and utilizing an event-number-specific user classification model. For example, the disclosed systems can train a user classification model based on a set of minimum prior event users who each satisfy a particular event number threshold. The event number threshold can correspond to a number of events that, when implemented by the target user identification system, cause the user classification model to converge. Upon training, the disclosed systems can detect an event associated with the client device of the target user, utilize the trained event-number-specific user classification model to identify the client device corresponding to the target user, and provide customized digital content to the client device of the target user.

Kourosh Modarresi, “Attributing Contributions of Digital Marketing Campaigns Towards Conversions”, Patent number: : 10475067, issued on 11/12/2019.

Abstract: Methods and systems for attributing contributions to digital marketing campaigns in achieving an action are described. In one or more implementations, first, second, and third order probabilities of a user taking the action are computed for each of a plurality of campaigns of a campaign path. Based on the probabilities, contributions are attributed to the campaigns of the campaign path in achieving the action.

Kourosh Modarresi, "Extracting Relevant Features from Electronic Marketing Data for Training Analytic Models”, Patent number: 10515378, issued on 12/24/2019.

Abstract: In certain embodiments, an analytical application accesses electronic marketing data that is automatically generated by interactions with marketing communications. The analytical application represents the set of electronic marketing data as a data matrix, in which columns of the matrix correspond to features of the data set. The analytical application selects a constraint for a singular value decomposition of the initial matrix and performs the singular value decomposition with the constraint. The constrained singular value decomposition derives, from the initial matrix, a matrix of singular vectors having a threshold number of rows with non-zero coefficients. The analytical application identifies certain columns from the initial matrix that correspond to the rows of the derived matrix with the non-zero coefficients and selects the features corresponding to those columns. The analytical application trains the analytical model using the selected features.

Kourosh Modarresi, “System and Method for Ranking and Selecting Data Features”, Patent number: 9348885, Issued on 05/24/2016.

Abstract: Example systems and methods of extracting the most informative data parameters from a set of data are provided. Large dimensionality data sets may reduced to a desired dimensionality while substantially preserving their real world interpretation so that the resultant reduced dimensionality set may still be effectively interpreted in light of a real world initial data set. The systems and method first complete the data set by filling in missing data in a manner that will not bias the resultant reduced data set. The system then selects the N most informative data parameters while minimizing reconstruction error.

Kourosh Modarresi, “Detection and Restoration of Erroneous Data”, Patent number: 9298540, Issued on 03/29/2016.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for detecting and restoring erroneous data. In cases that a data entry within a data matrix is determined to be erroneous, the data entry can be restored using a replacement value calculated in accordance with other data from the data matrix. In particular, the number of dimensions used to calculate the replacement value can be reduced from the complete set of dimensions to avoid unnecessary noise data that may impact corrected data values.

Kourosh Modarresi, “Performing Predictive Analysis on Usage Analytics”, Patent number: 9609074, issued on 3/28/2017.

Abstract: Methods for predicting future data based on time-dependent data with increased accuracy include generating resampled datasets from a base dataset having at least one time dependent characteristic. Generating the resampled datasets includes randomly resampling data points in the base dataset to increase a pool of data for predicting future data while at least partially maintaining one or more time dependent characteristics of the base dataset. One or more embodiments apply a modified bootstrapping algorithm to the base dataset to generate the resampled datasets. Predicting the future data includes applying a time series algorithm to the resampled datasets to generate a predicted future dataset with improved accuracy by utilizing the time dependent characteristic maintained in the resampled datasets.

Kourosh Modarresi, “Transformation of Network Activity Data for User Identification", Patent number: 10037417, issued on 7/31/2018.

Abstract: Techniques of identifying users involve automatically determining whether new user activity data received by a server is associated with a user known to the server. Along these lines, a server collects data representing network activity of a group of users. The data collected takes the form of a table, or matrix, with each entry corresponding to a respective user and having values of a respective set of fields. The server may then use this data as training data in developing a model for predicting whether new activity data corresponds to one of the group of users or a new user not in the group of users.

Kourosh Modarresi, “Personalized Recommendations Using Localized Regularization”, Patent number: 10152545, issued on 12/11/2018.

Abstract: A subset of items that can be identified, promoted, or recommended to the user is determined based in part on rankings or other feedback that the user has given to other items in the set. The techniques discussed herein employ localized regularization to generate estimated values for the unknown values. Regularization refers to adding information into the system in order to generate the unknown values. This additional information of the system is an estimate, and is generated based on the known properties of the system. The techniques discussed herein employ localized regularization, which refers to estimating additional information based on the particular user for which the unknown values are being generated. In contrast to employing global regularization that treats all users in the system the same, the localized regularization discussed herein treats each user independently of the other users.

Kourosh Modarresi, “Feature Summarization Filter with Applications Using Data Analytics”, Patent number: 10275628, issued on 4/30/2019.

Abstract: A data-analytics application may be optimized for implementation on a computing device for conserving computing or providing timely results, such as a prediction, recommendation, inference, or diagnosis about a monitored system, process, event, or a user, for example. A feature filter or classifier is generated and incorporated into or used by the application to provide the optimization. The feature filter and classifier are generated based on a set of significant features, determined using a data condensation and summarization process, from a high-dimensional set of available features characterizing the target. For example, a process that includes utilizing combined sparse principal component analysis with sparse singular value decomposition and applying k-medoids clustering may determine the significant features. Insignificant features may be filtered out or not used, as information represented by the insignificant features is expressed by the significant features.

Kourosh Modarresi, “Personalization of digital content recommendations”, Patent number: 10810616, issued on 10/20/2020.

Abstract: Personalization techniques for digital content recommendations are described. In one example, a hybrid model is used to form recommendations for individual users, groups of individual users, and so on. The hybrid model may also employ a latent factor model, which is configured to employ an implicit similarity approach to recommendations. The recommendations formed by these models are then used to generate a third, final, recommendation. As part of this, a weighting may be employed to weight a contribution of recommendations from the collaborative filter model and latent factor model in order to further personalize a recommendation for a user. Moreover, through application of localized regularization, for which every user is treated separately and also every content is considered independently, more personalization is achieved.

Kourosh Modarresi, Khashayar Khosravi, “Performance-based digital content delivery in a digital medium environment”, Patent number: 10853840, issued on 12/1/2020.

Abstract: Performance-based digital content delivery in a digital medium environment is described. Initially, different items of a collection of digital content are delivered to a substantially equal number of users. The collection is then iteratively tested to identify which content item achieves a desired action (e.g., conversion) at a highest rate. During the iterative test, data describing user interaction with the delivered content is collected. Based on the collected data, measures of achievement are determined for the different content items. Measures of statistical guarantee are also computed that indicate an estimated accuracy of the achievement measures. Responsive to determining that a condition for ending the test has not yet occurred, an optimized allocation is computed for delivery of the content by applying one of multiple allocation optimization techniques. The particular technique applied is based on the condition for ending the test and a type of statistical guarantee associated with the test.

Kourosh Modarresi, “Techniques for determining whether to associate new user information with an existing user”, Patent number: 10909145, issued on 2/2/2021.

Abstract: Systems and methods for determining whether to associate new user information with an existing user are disclosed. One embodiment involves clustering users in a set of users into clusters based on similarities of personal or behavioral features of the users. The embodiment further involves receiving new user information relating to a user using a device that provides the new user information via a computer network. A best matching cluster of the clusters is identified based on similarity of personal or behavioral features of the new user information to personal or behavioral features of the best matching cluster. The embodiment compares the personal or behavioral features of the new user information with personal or behavioral features of an existing user in the best matching cluster to determine whether to associate the new user information with the existing user or to assign it as a new (previously non-existent and unknown) user.

Kourosh Modarresi, “Personalized recommendations using localized regularization”, Patent number: 10922370, issued on 2/16/2021.

Kourosh Modarresi, “Predicting a number of links an email campaign recipient will open”, Patent number: 10997524, issued on 5/4/2021.

Abstract: Techniques for predicting a number of links an email campaign recipient will open are described. Elements in a dataset related to an email campaign are modeled using a tree structure, where nodes of the tree represent features of each element. A mean squared error is computed of an outcome for each of the elements to determine a weight for each respective tree. The weights are then regularized by applying a penalty, such as an elastic net penalty, to each of the weights. Then, the weights are applied to each of the trees. A weighted average of all of the outcomes of the trees is calculated, where the weighted average represents a prediction of an outcome resulting from a set of feature values. The feature values correspond to the nodes of each of the trees.

Kourosh Modarresi, Hongyuan Yuan, Charles Menguy, “Automatically generating meaningful user segments”, Patent number: 11023495, issued on 6/1/2021.

Abstract: Systems, methods, and non-transitory computer-readable media (systems) are disclosed for generating meaningful and insightful user segment reports based on a high dimensional data space. In particular, in one or more embodiments, the disclosed systems utilize a relaxed bi-clustering model to automatically identify user segments in a data space including datasets of features specific to individual users. In at least one embodiment, the disclosed systems identify and include users in automatically generated user segments even though those users are associated with some, but perhaps not all, of the features as other members in the automatically generated user segments.

Kourosh Modarresi, Abdurrahman Ibn Munir, “Categorical data transformation and clustering for machine learning using data repository systems”, Patent number: 11036811, issued on 6/15/2021.

Abstract: Categorical data transformation and clustering techniques and systems are described for machine learning. These techniques and systems are configured to improve operation of a computing device to support efficient and accurate use of categorical data, which is not possible using conventional techniques. In an example, categorical data is received by a computing device that includes a categorical variable having a non-numerical data type for a number of classes. The categorical data is then converted into numerical data based on clustering used to generate a plurality of latent classes.

Kourosh Modarresi, “Anonymous cross-device, cross-channel, and cross-venue user identification using adaptive deep learning”, Patent number: 11080376, issued on 8/3/2021.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for digital user identification across different devices, channels, and venues. Generally, digital interactions of a user can reveal a pattern of digital behavior that can be detected and assigned to the user, and a classifier can be learned to identify the user. Various types of digital interaction data may be utilized to identify a user, including device data, geolocation data associated with a user device, clickstream data or other attributes of web traffic, and the like. Anonymity can be provided by only utilizing behavioral-based user data. Digital interaction data can be encoded and fed into a multi-class classifier (e.g., deep neural network, support vector machine, random forest, k-nearest neighbors, etc.), with each user corresponding to a different class. New users can be detected and used to automatically grow a deep neural network to identify additional classes for the new users.

Kourosh Modarresi, Jamie Mark Diner, Elizabeth T. Chin, Aran Nayebi, “Segment valuation in a digital medium environment”, Patent number: 11182804, issued on 11/23/2021.

Abstract: Segment valuation techniques usable in a digital medium environment are described. To do so, a segment valuation system first identifies the attributes that are significant in achievement of a desired metric (e.g., conversion) and then values segments based on those significant attributes. Attributes are selected from the trained model based on significance of those attributes towards achieving the desired metric. A valuation of a segment may then be calculated based on the valuations of these attributes. For example, inclusion of the selected attributes within a segment, and the valuations of those selected attributes, is then used by the segment valuation system to generate data describing a value of the segment towards achieving the metric.

Kourosh Modarresi, “Generating prediction models in accordance with any specific data sets”, Patent number: 11443015, issued on 9/13/2022.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for facilitating generation of prediction models. In some embodiments, a predetermined number of parameter value sets is identified. Each parameter value set includes a plurality of parameter values that represent corresponding parameters within a time series model. The parameter values can be selected in accordance with stratified sampling to increase a likelihood of prediction accuracy. The parameter value sets are input into a time series model to generate a prediction value in accordance with observed time series data, and the parameter value set resulting in a least amount of prediction error can be selected and used to generate a time series prediction model (ARIMA, AR, MA, ARMA) with corresponding model parameters, such as p, q, and/or k, subsequently used to predict values.

Kourosh Modarresi, Hongyuan Yuan, Charles Menguy, “Machine-learning techniques for evaluating suitability of candidate datasets for target applications”, Patent number: 11481668 , issued on 10/25/2022.

Abstract: Techniques disclosed herein relate generally to evaluating and selecting candidate datasets for use by software applications, such as selecting candidate datasets for training machine-learning models used in software applications. Various machine-learning and other data science techniques are used to identify unique entities in a candidate dataset that are likely to be part of target entities for a software application. A merit attribute is then determined for the candidate dataset based on the number of unique entities that are likely to be part of the target entities, and weights associated with these unique entities. The merit attribute is used to identify the most efficient or most cost-effective candidate dataset for the software application.

Kourosh Modarresi, Abdurrahman Ibn Munir, “Categorical data transformation and clustering for machine learning using natural language processing”, Patent number: 11531927, issued on 12/20/2022.

Abstract: Categorical data transformation and clustering techniques and systems are described for machine learning using natural language processing. These techniques and systems are configured to improve operation of a computing device to support efficient and accurate use of categorical data, which is not possible using conventional techniques. In an example, categorical data is received by a computing device that includes a categorical variable having a non-numerical data type for a number of classes. The categorical data is then converted into numerical data using natural language processing. Data is then generated by the computing device that includes a plurality of latent classes. This is performed by clustering the numerical data into a number of clusters that is smaller than the number of classes in the categorical data.

Kourosh Modarresi, Yi Liu, Paresh P. Shenoy, Aran Nayebi, Pradeep Saikalyanachakravarthi Javangula, “User data overlap determination in a digital medium environment”, Patent number: 11651382, issued on 5/16/2023.

Abstract: User data overlap determination in a digital medium environment is described. Initially, a user selects segments of user data for which a determination of overlap is to be made. For example, the user selects a segment representing users that are working professionals and a segment representing users that are mothers, such that working-mother users may correspond to the overlap. Regardless of the particular segments selected, an indication of those segments is received. One of multiple different overlap determining techniques—which can include a combined MinHash and HyperLogLog (HLL) technique and an Inclusion-Exclusion technique—may be selected for computing the overlap based on a number of segments indicated and numbers of users represented by the segments. The selected overlap determining technique is then used to compute the user data overlap between the indicated segments. Digital content including values indicative of the determined overlap is generated for presentation to a user.

Kourosh Modarresi, Hongyuan Yuan, Charles Menguy, “Machine-learning techniques for evaluating suitability of candidate datasets for target applications”, Patent number: 11704598, issued on 7/18/2023.

Kourosh Modarresi, Jamie Mark Diner, “Matrix completion and recommendation provision with deep learning”, Patent number: 11770571, issued on 9/26/2023.

Abstract: Matrix completion and recommendation provision with deep learning is described. A matrix manager system imputes unknown values of incomplete input matrices using deep learning. Unlike conventional techniques, the matrix manager system completes incomplete input matrices using deep learning regardless of whether an input matrix represents numerical, categorical, or a combination of numerical and categorical attributes. To enable a machine-learning model (e.g., an autoencoder) to complete a matrix, the matrix manager system initially encodes the matrix. This involves normalizing known values of numerical attributes and categorically encoding known values of categorical attributes. The matrix manager system performs categorical encoding by replacing information of a given categorical attribute (e.g., an attribute column) with replacement information for each possible value of the attribute (e.g., new columns for each possible value).

Kourosh Modarresi, Hongyuan Yuan, Charles Menguy, “Automatically generating user segments”, Patent number: 11809455, issued on 11/7/2023.

Michael Craig Burkhart, Kourosh Modarresi, “Digital experience enhancement using an ensemble deep learning model”, Patent number: 11816562, issued on 11/14/2023.

Abstract: A digital experience enhancement system includes an ensemble deep learning model that includes an estimator ensemble and a neural network. The ensemble deep learning model is trained to generate a digital experience enhancement recommendation from an enhancement request. The ensemble deep learning model receives the enhancement request, which is input to the estimator ensemble. The estimator ensemble uses various different machine learning systems to generate estimator output values. The neural network uses the estimator output values from the estimator ensemble to generate a digital experience enhancement recommendation. The digital experience generation system then uses this digital experience enhancement recommendation to enhance the digital experience.

Kourosh Modarresi, Jamie Mark Diner, Elizabeth T. Chin, Aran Nayebi, “Segment valuation in a digital medium environment”, Patent number: 11869021, issued on 1/9/2024.

Patents Submitted, Pending:

Kourosh Modarresi, “Predicting Outcomes of a Modeled System Using Dynamic Features Adjustment”, P3145US01 - Application - US - 14/097,998, Filed on 12/05/2013.
Kourosh Modarresi, “Determining and Analyzing Key Performance Indicators, P3724US01”, Application - US - 14/167,984- Filed on 01/29/2014.
Kourosh Modarresi, “Time Series Forecasting in the Web Browser”, P5475US01 - Application - US - 14/919,395, Filed on 10/21/2015.
Kourosh Modarresi, Khashayar Khosravi, “Optimal Detection of the Winning Offers in a Campaign”, P6476-US, filed on 11/10/2016.
Kourosh Modarresi, Aran Nayebi, Jamie Diner, Elizabeth Chin, “Business Valuation of Segments and Attributes”, P6488-US, filed on 11/17/2016.
Kourosh Modarresi, Yi Liu, “Security Breach Detection in a Digital Medium Environment”, P6521-US, filed on 1/13/2017.
Kourosh Modarresi with Paresh Shenoy, Aran Nayebi, Yi Liu, “User Data Overlap Determination in a Digital Medium Environment" , P6751-US, filed on 5/31/2017.
Kourosh Modarresi with Jamie Diner, “Determining Insights from Different Data Sets”, P7198-US, filed on 11/9/2017.
Kourosh Modarresi with Jisha Vadake Muthiyil, Charles Menguy, Iulian Radu, Aran Nayebi, Yi Liu, “Segment Extension Based on Lookalike Selection”, P7144-US, filed on 1 /8/2018.
Kourosh Modarresi , “Gen-AI Tuning and Deploying for "Recommender Systems ”, P209538-US, filed on 7/26/2024.

Page updated

Google Sites

Report abuse