公开(公告)号：US20220309391A1

公开(公告)日：2022-09-29

申请号：US17216475

申请日：2021-03-29

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Dhavalkumar C. PATEL ,  Si Er HAN ,  Jiang Bo KANG

IPC分类号： G06N20/00 ,  G06N5/04 ,  G06F16/28

摘要： Methods, computer program products, and systems are presented. The method, computer program products, and systems can include, for instance: examining an enterprise dataset, the enterprise dataset defined by enterprise collected data; selecting one or more synthetic dataset in dependence on the examining, the one or more synthetic dataset including data other than data collected by the enterprise; training a set of predictive models using data of the one or more synthetic dataset to provide a set of trained predictive models; testing the set of trained predictive models with use of holdout data of the one or more synthetic dataset; and presenting prompting data on a displayed user interface of a developer user in dependence on result data resulting from the testing, the prompting data prompting the developer user to direct action with respect to one or more model of the set of predictive models.

公开(公告)号：US20220327058A1

公开(公告)日：2022-10-13

申请号：US17654965

申请日：2022-03-15

申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人： Long VU ,  Bei CHEN ,  Xuan-Hong DANG ,  Peter Daniel KIRCHNER ,  Syed Yousaf SHAH ,  Dhavalkumar C. PATEL ,  Si Er HAN ,  Ji Hui YANG ,  Jun WANG ,  Jing James XU ,  Dakuo WANG ,  Gregory BRAMBLE ,  Horst Cornelius SAMULOWITZ ,  Saket K. SATHE ,  Wesley M. GIFFORD ,  Petros ZERFOS

IPC分类号： G06F12/0871 ,  G06N20/00

摘要： 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.