International Business Machines Corporation

Dhavalkumar C Patel

Arun Kwangil Iyengar

Shrey Shrivastava

Nianjun Zhou

Anuradha Bhamidipaty

Jing James Xu

Bei Chen

Dakuo Wang

Si Er Han

Ji Hui Yang

Chandrasekhara K Reddy

Syed Yousaf Shah

Jeffrey Owen Kephart

Jayant R Kalagnanam

Chuang Gan

Jun Song Wang

Emmanuel Yashchin

Dung Tien Phan

Peter Daniel Kirchner

Horst Cornelius Samulowitz

Long H Vu

Gregory Bramble

Saket Sathe

Xuan-Hong Dang

Young Min Lee

Petros Zerfos

Christian Makaya

Jun Wang

Wesley M Gifford

Kyong Min Yeo

Nam H Nguyen

Edward John Pring

Abel Nicolas Valente

Arunima Chaudhary

Daniel Karl I Weidele

John Dillon Eversman

Voranouth Supadulya

Hui Qi

Long Vu

Markus Müller

An example operation may include one or more of executing a first processing element among a sequence of processing elements within a data processing pipeline on input data to generate a first output, transferring the first output and context associated with the first processing element from the first processing element to a second processing element among the sequence of processing elements, within the data processing pipeline, executing the second processing element on the first output and the context to generate a second output, and storing the second output in memory.

Pipeline with context transfer

Techniques for model evaluation and selection are provided. A plurality of models trained to generate predictions at each of a plurality of intervals is received, and a plurality of model ensembles, each specifying one or more of the plurality of models for each of the plurality of intervals, is generated. A test data set is received, where the test data set includes values for at least a first interval of the plurality of intervals and does not include values for at least a second interval of the plurality of intervals. A first model ensemble, of the plurality of model ensembles, is selected based on processing the test data set using each of the plurality of model ensembles.

Determining and selecting prediction models over multiple points in time using test data

Methods and systems to provide a form of probabilistic labeling to associate an outage with a disturbance, which could itself be either known based on the available data or unknown. In the latter case, labeling is especially challenging, as it necessitates the discovery of the disturbance. One approach incorporates a statistical change-point analysis to time-series events that correspond to service tickets in the relevant geographic sub-regions. The method is calibrated to separate the regular periods from the environmental disturbance periods, under the assumption that disturbances significantly increase the rate of loss-causing events. To obtain the probability that a given loss-causing event is related to an environmental disturbance, the method leverages the difference between the rate of events expected in the absence of any disturbances (baseline) and the rate of actually observed events. In the analysis, the local disturbances are identified and estimators of their duration and magnitude are provided.

Associating disturbance events to accidents or tickets

Disclosed embodiments provide techniques for estimating imputation algorithm performance. Multiple imputer algorithms are selected, and an evaluation of how well each of the imputer algorithms can estimate the missing data is performed. Disclosed embodiments obtain an imputer candidate dataset (ICD). The imputer candidate dataset is compared to the incomplete data range, and a similarity metric is determined between the data range and the ICD. When the similarity metric exceeds a predetermined threshold, an imputer evaluation dataset (IED) is created from the ICD by removing one or more data points from the ICD. Each imputer algorithm is evaluated by applying the IED to it, and computing an imputer evaluation metric based on its performance. The multiple imputer algorithms are ranked based on the imputer evaluation metric. The best ranked imputer algorithm can then be selected for use on the incomplete data range within the measurement dataset.

Data gap mitigation

A computer implemented federated learning method of predicting failure of assets includes generating a local model at a local site for each of the cohorts and training the local model on local data for each of the cohorts for each failure type. The local model is shared with a central database. A global model is created based on an aggregation of a plurality of the local models from a plurality of the local sites. At each of the plurality of local sites, one of the global model and the local model is chosen for each of the cohorts. The chosen model operates on local data to predict failure of the assets. The utilized features include partitioning features of the assets into static features, semi-static features, and dynamic features, and forming cohorts of the assets based on the static features and the semi-static features.

Federated learning for multi-label classification model for oil pump management

Using exported data of a machine learning model and a model training environment specification, a resource usage specification and a code module usage specification of the model are identified. A code module installation specification is determined from a code module requirements specification and a target execution environment specification. The code modules specified by the code module installation specification are caused to be installed in the target execution environment. Using data of the updated target execution environment, the updated target execution environment is validated for execution of the model. Execution of the model in the updated target execution environment is simulated. The model is deployed in the updated target execution environment responsive to the simulating being successful.

Automated machine learning model deployment

A computer implemented method of preparing process data for use in an artificial intelligence (AI) model includes collecting and storing raw data as episodic data for each episode of a process. An episode data generator assigns an episode identifier each set of episodic data. The raw data per episode is transformed into a standardized episodic data format that is usable by the AI model. Metrics are assigned to the episodic data and the episodic data is aggregated in an episode store. The data in the episode store is used by a feature extraction and learning module to extract and rank features.

Dynamic and continuous composition of features extraction and learning operation tool for episodic industrial process

Techniques for generating model ensembles are provided. A plurality of models trained to generate predictions at each of a plurality of intervals is received. A respective prediction accuracy of each respective model of the plurality of models is determined for a first interval of the plurality of intervals by processing labeled evaluation data using the respective model. Additionally, a model ensemble specifying one or more of the plurality of models for each of the plurality of intervals is generated, comprising selecting, for the first interval, a first model of the plurality of models based on (i) the respective prediction accuracies and (ii) at least one non-error metric.

Determining and selecting prediction models over multiple points in time

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.

Dynamic discovery and correction of data quality issues

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

Systems, computer-implemented methods, and computer program products to facilitate visualization of a model selection process 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 an interaction backend handler component that obtains one or more assessment metrics of a model pipeline candidate. The computer executable components can further comprise a visualization render component that renders a progress visualization of the model pipeline candidate based on the one or more assessment metrics.

Visualization of a model selection process in an automated model selection system

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

Embodiments of the invention are directed a computer-implemented method for efficiently assessing data quality metrics. A non-limiting example of the computer-implemented method includes receiving, using a processor, a plurality of updates to data points in a data stream. The processor is further used to provide a plurality of data quality metrics (DQMs), and to maintain information on how much the plurality of DQMs are changing over time. The processor also maintains information on computational overhead for the plurality of DQMs, and also updates data quality information based on the maintained information.

Efficient real-time data quality analysis

Embodiments of the invention are directed a computer-implemented method for assessing data quality. A non-limiting example of the computer-implemented method includes using a processor to receive a plurality of updates to data points in a data stream. The processor is further used to compute instances of a data quality metric (DQM) from the data points in the data stream. The instances of the DQM are configured to differentiate the data points in the data stream by time and assign a higher weight to the instances of the DQM computed from more recent data points in the data stream. The instances of the DQM are continuously updated as more of the data points are received by the processor while limiting cycles of the processor consumed by updating the instances of the DQM to a threshold.

Real-time data quality analysis

Based on at least one manufacturing process characteristics associated with a manufacturing process, a prediction time at which to execute a selected machine learning model selected from multiple trained machine learning models is determined, and at the prediction time, the selected machine learning model is executed. Executing the selected machine learning model predicts a control set point for future values of state variables of the manufacturing process, for controlling the manufacturing process. Based on at least one of the manufacturing process characteristics, a learning time at which to train a machine learning model is determined, and at the learning time, the machine learning model is trained based on historical process data associated with the manufacturing process.

Growing community of inventors

White Plains, NY, United States of America

Dhavalkumar C Patel