International Business Machines Corporation

Avijit Chatterjee

John J Thomas

Rajiv V Joshi

Swaminathan Balasubramanian

Wendy L Wang

Sean James Martin

Jordi A Albornoz

Lee David Feigenbaum

Lonnie A McCullough

Alfred Inselberg

Herschel J R Weintraub

Aleksandr Evgenyevich Petrov

Vernon Ralph Austel

Vinay R Dandin

Ricardo Balduino

Bernard Dimsdale

A method, system, and computer program product are provided for generating a predictive model. A processor(s) obtains a raw data set (peptide libraries) of patients designated as diagnosed/pre-diagnosed with a condition or not diagnosed with the condition. The processor(s) segments the raw data set into a pre-defined number of groups and separates out a holdout group. The processor(s) performs a principal component analysis on the remaining groups to identify, based on a frequency of features in the remaining groups, common features (principal components) in the remaining groups and weighs the common features based on frequency of occurrence. The processor(s) determines a smallest number of the principal components that yields a pre-defined level of validation accuracy. The processor(s) generates a predictive model, by utilizing the smallest number for a best fit in a logistic regression model. The predictive model provides binary outcomes.

Library screening for cancer probability

Method and apparatus for generating profiles using machine learning and influencing online interactions are provided. The methods include generating a user profile specifying a plurality of attribute values for a plurality of principle attributes, by processing a corpus of electronic documents using a first trained machine learning model. In an embodiment, the method further comprises generating a provider profile specifying a plurality of attribute values for the plurality of principle attributes, for each of a plurality of providers, by processing a respective corpus of electronic documents associated with each respective provider using a second trained machine learning model. A plurality of match coefficients based on comparing the user profile and the plurality of provider profiles are determined. Finally, one or more online interactions between the user and the target provider are influenced based on the determined match coefficients.

Building and matching electronic standards profiles using machine learning

Method and apparatus for generating profiles using machine learning and influencing online interactions are provided. The methods include receiving, from a first user of a plurality of users, a first set of electronic documents, where each electronic document in the first set of electronic documents corresponds to a respective user in the plurality of users. The methods also include identifying a plurality of user profiles, where each of the plurality of user profiles was generated by processing a corpus of electronic documents associated with each respective user using a first trained machine learning model. The methods include determining a plurality of match coefficients, based on comparing a plurality of user profiles associated with each respective user in the plurality of users, filtering the first set of electronic documents based on the plurality of match coefficients, and providing the filtered first set of electronic documents to the first user.

Building and matching electronic user profiles using machine learning

Disclosed aspects relate to managing a set of offers using a dialogue. An adaptive profile may be received with respect to a client. The adaptive profile may indicate a set of client profile data, a set of client event data, and a set of client context data. A dialogue may be established with the client based on the adaptive profile. A set of offers may be resolved by an offer management engine based on the dialogue. The set of offers may be presented to the client.

Managing a set of offers using a dialogue

In a general purpose computer, a method of extracting snippets includes receiving textual content and a plurality of available topics, dividing the textual content into a plurality of snippets, converting each of the snippets to a vector, determining a distance between coadjacent snippets of the plurality of snippets in the textual content, determining an update to the plurality of snippets by merging each of the pairs of coadjacent snippets having a respective distance less than a second threshold, wherein an updated plurality of snippets includes merged snippets, generating a plurality of clusters from the updated plurality of snippets, each cluster associated with one topic selected from the plurality of available topics, and generating, for each of the snippets of the updated plurality of snippets, an affinity score for each of the clusters, each affinity score measuring an assignment strength of a given snippet to a given cluster, and a dominant topic among the at least one identified topic.

Incremental discovery of salient topics during customer interaction

Methods, systems, and articles of manufacture for managing global annotations made for data elements that may be instantiated (e.g., displayed) by a variety of different type applications are provided. By anchoring the global annotations to the data element, rather than the particular data source containing the data element at the time the data element was annotated, the annotation may be retrieved from any application that instantiates or displays it.

Creation and retrieval of global annotations

Method and system for creation and retrieval of global annotations

A system for detecting lines in images using line neighborhoods and a parallel coordinate transformation. The process introduces the concept of line neighborhoods to accommodate the uncertainty in line detection arising from image noise. Because line neighborhoods in Cartesian coordinates have ambiguous and unbounded regions and always overlap one another, a parallel coordinate transform is used to transform Cartesian coordinate image plane line segments to points in a bounded and nonambiguous region of the parallel coordinate transform plane. Line detection then becomes a simple problem of detecting point clusters in the parallel coordinate transform plane.

System using parallel coordinates for automated line detection in noisy

A multi-variate data set is displayed in a plurality of multi-dimensional presentations on a computer having a graphical interface and a keyboard input. The data set includes a plurality of independent variables and, for each independent variable, a plurality of dependent variables. A computer displays the data set in parallel coordinate form on the graphical interface so that each dependent variable of the data set is presented as a series of values along an axis, plural axes arranged in parallel. The graphical interface provides a polygonal line which connects a value on each parallel axis and illustrates a relationship between an independent variable and the dependent variables appearing on each axis. The user input enables a user to superimpose on the graphical interface graphical delimiters either on or between two succeeding parallel axes. The graphical delimiters identify a data subset that includes at least one independent variable and adjacent dependent variables. In response to placement of the graphical delimiters, the computer modifies a presentation of any polygonal lines connecting the adjacent dependent variables and which lies between the graphical delimiters, and differentiates then from other polygonal lines which represent remaining data subsets of the data set. The computer further enables an illustration of the delimited data subset in Cartesian coordinates.

Growing community of inventors

White Plains, NY, United States of America

Avijit Chatterjee