International Business Machines Corporation

Xuan-Hong Dang

Petros Zerfos

Syed Yousaf Shah

Jing James Xu

Bei Chen

Dakuo Wang

Si Er Han

Ji Hui Yang

Peter Daniel Kirchner

Horst Cornelius Samulowitz

Long H Vu

Dhavalkumar C Patel

Saket Sathe

Gregory Bramble

Mudhakar Srivatsa

Chuang Gan

Jun Song Wang

Nancy Anne Greco

Vijay Arya

Jun Wang

Wesley M Gifford

Joshua M Rosenkranz

Raji Lakshmi Akella

Long Vu

Yunqi Guo

Ashley Potter

Milton Orlando Laverde Echeverria

Providing time-series forecasting by receiving target variable data and exogenous variable data, training a plurality of time-series models according to the target variable data and the exogenous variable data, determining a historical error for each of the plurality of time series models, and providing a time-series forecasting model having a lowest historical error.

Time series forecasting with exogenous variable data

A first set of data associated with assets can be received. An ontology graph can be constructed based on the first set of data. A second set of data associated with the assets can be received, the second set of data having a first frequency of sampling. Based on the second set of data, nodes of the ontology graph representing the assets can be characterized. A third set of data associated with the assets can be received, the third set of data having a second frequency of sampling. The third set of data can include real time data associated with the assets. Based on the third set of data and information associated with the assets represented by the ontology graph, a deep learning neural network can be trained to predict a future state of at least one asset of the assets and discover dynamic mutual impact of the assets.

Asset health identification from multi-modality data analysis

Aspects of the invention include techniques for decomposing trend and seasonality components in a forecast of parametric time series data. A non-limiting example method includes receiving time series data that includes a plurality of values taken over a first period of time. A forecast is generated using the time series data. The forecast can include one or more predicted values over a second period of time. The forecast is decomposed into N components and 2coalitions are defined for the N components. A coalition value is determined for each coalition of the 2coalitions.

Trend and seasonality decomposition

To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Automated time series forecasting pipeline generation

Embodiments relate to a system, program product, and method for employing deep learning techniques to fuse data across modalities. A multi-modal data set is received, including a first data set having a first modality and a second data set having a second modality, with the second modality being different from the first modality. The first and second data sets are processed, including encoding the first data set into one or more first vectors, and encoding the second data set into one or more second vectors. The processed multi-modal data set is analyzed, and the encoded features from the first and second modalities are iteratively and asynchronously fused. The fused modalities include combined vectors from the first and second data sets representing correlated temporal behavior. The fused vectors are then returned as output data.

Fusing multimodal data using recurrent neural networks

Techniques regarding multivariate time series data analysis are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that generates a machine learning model that discovers a dependency between multivariate time series data using an attention mechanism controlled by an uncertainty measure.

Determining multivariate time series data dependencies

Techniques regarding one or more automated machine learning processes that analyze time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that selects a machine learning pipeline for meta transfer learning on time series data by sequentially allocating subsets of training data from the time series data amongst a plurality of machine learning pipeline candidates.

Automated machine learning pipeline generation

Techniques are provided for the automated risk assessment of a document. In one embodiment, the techniques involve mapping, via a risk assessment engine, one or more sentences in a first document to one or more risk categories, identifying, via a classification engine, risk-associated language of the one or more sentences based on the one or more risk categories, mapping, via a risk assessment engine, the risk-associated language of the one or more sentences to one or more risk criterion of a risk criterion document, and generating, via a risk assessment engine, a first risk assessment based on the one or more risk criterion of the risk criterion document.

Automatic contract risk assessment based on sentence level risk criterion using machine learning

For a plurality of hosts, observe first time-varying characteristics including network throughput, central processing unit (CPU) usage, and/or memory usage; second time-varying characteristics including software configuration; and time-invariant characteristics including hardware configuration, at a plurality of timestamps. Construct a restricted HMM configured to predict actual host states, wherein the first time-varying characteristics include observed variables. The current observed variables depend on current values of the hidden variables and prior timestamp distribution of the observed variables. The former in turn depend on prior timestamp values of the hidden variables, the time-invariant characteristics of the hosts. and current timestamp values of the second time-varying characteristics. Estimate parameters of the restricted HMM; run the restricted HMM with the estimated parameters for each of the hosts; analyze the results to identify at least one of the hosts which has a potential cybersecurity issue; and take at least one remedial action.

Predicting condition of a host for cybersecurity applications

Growing community of inventors

Chappaqua, NY, United States of America

Xuan-Hong Dang