International Business Machines Corporation

Vitobha Munigala

Diptikalyan Saha

Arvind Agarwal

Geetha Adinarayan

Sattwati Kundu

Mitesh H Vasa

Ankush Gupta

Shanmukha Chaitany Guttula

Arun Kumar

Hima Patel

Shashank Mujumdar

Philips George John

Riddhiman Dasgupta

Nicholas Gomez Phan

A method, system, and computer program product for explaining predictions made by black box time series models. The method may include identifying a black box time series model. The method may also include predicting one or more time instances using the black box time series model. The method may also include selecting a predicted time instance from the predicted data. The method may also include receiving training data for the black box time series model. The method may also include generating a set of white box time series models similar to the black box time series model. The method may also include selecting a preferred white box time series model. The method may also include analyzing behavior of the preferred white box time series model. The method may also include generating an explanation illustrating why the black box time series model forecasted the predicted time instance.

Explanation for time series forecasting models

Processing within a computing environment is facilitated using a corpus processing system to assess and enhance quality of a corpus of unstructured documents for a specified task. The processing includes referencing, by a corpus processing engine, the corpus of unstructured documents to obtain unstructured document data, and applying, by a corpus quality metrics engine, a set of quality metrics to the document data to obtain a set of quality metric scores. Further, the process includes automatically selecting, by a quality metric selection engine, a subset of task-relevant quality metrics using the quality metric scores and the specified task, and automatically transforming, at least in part, multiple documents of the corpus to remediate one or more identified issues with the documents. The automatically transforming results in remediated documents tuned for the specified task, which are provided for the specified task to be performed.

Corpus quality processing for a specified task

A system, computer program product, and method are presented for providing replacement data for data in a time series data stream that has issues indicative of errors, where the data issues and the replacement data are related to one or more KPIs. The method includes determining one or more predicted replacement values for potentially erroneous data instances in the time series data stream. The method further includes resolving the potentially erroneous data instances with one predicted replacement value of the one or more predicted replacement values in the time series data stream.

Data quality-based computations for KPIs derived from time-series data

One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a revision different than another of the at least two documents; identifying, within each of the at least two documents, portions corresponding to groups of text containing a conceptual unit; assigning at least a subset of the identified portions to a category type corresponding to a topic of a given portion, wherein the assigning comprises (i) generating a semantic tag for the identified portions in the subset and (ii) tagging the identified portions in the subset with the semantic tag; and determining changes between the at least two documents, wherein the determining comprises (iii) aligning given portions across the at least two documents based upon a relationship between the given portions across the at least two documents, (iv) identifying semantic differences between the aligned portions, and (v) identifying any remaining unaligned portions.

Identification of changes between document versions

Methods, systems, and computer program products for contrasting document-embedded structured data and generating summaries thereof are provided herein. A computer-implemented method includes extracting two or more tables from two or more input documents, wherein each of the two or more input documents comprises structured data and unstructured data; normalizing the two or more extracted tables using one or more alignment techniques; determining at least one of (i) one or more differences and (ii) one or more similarities across the two or more extracted tables by performing a comparison of the two or more normalized tables; deriving one or more insights from the comparison by applying at least one analytical model to the at least one of the one or more determined differences and one or more determined similarities; and outputting at least a portion of the one or more insights to at least one user.

Contrasting document-embedded structured data and generating summaries thereof

A system, computer program product, and method are presented for providing confidence values for replacement data for data that has issues indicative of errors, where the data issues, the replacement data, and confidence values are related to one or more KPIs. The method includes identifying one or more potentially erroneous data instances and determining one or more predicted replacement values for the potentially erroneous data instances. The method further includes determining a confidence value for each predicted replacement value and resolving the one or more potentially erroneous data instances with one predicted replacement value of the one or more predicted replacement values. The method also includes generating an explanatory basis for the resolution of the one or more potentially erroneous data instances.

Data quality-based confidence computations for KPIs derived from time-series data

One embodiment provides a method, including: obtaining at least two documents, wherein one of the at least two documents comprises a different revision of another of the at least two documents; identifying a structure of each of the at least two documents by parsing each of the at least two documents to extract text from each of the at least two documents; aligning sections of the at least two documents, wherein the aligning comprises matching a section from one of the at least two documents and a corresponding section from another of the at least two documents; identifying at least one difference between the at least two documents; assigning a semantic label to the identified at least one difference; and providing a summary of the identified at least one difference by compressing the text surrounding the identified at least one difference using the assigned semantic label.

Growing community of inventors

Secunderabad, India

Vitobha Munigala