International Business Machines Corporation

Massimiliano Mattetti

Elizabeth Daly

Oznur Alkan

Bei Chen

Rahul Nair

Inge Lise Vejsbjerg

Adi Ionel Botea

Dennis Wei

Alan Zwiren

Karthikeyan Natesan Ramamurthy

Yunfeng Zhang

Abel Nicolas Valente

Pablo Pedemonte

Alice J Chang

Xiaoxi Tian

Benjamin Dubiel

Sanjmeet Abrol

Weiwei Li

Embodiments of the invention are directed to a computer-implemented method. A non-limiting example of the computer-implemented method includes accessing, using an explanation generator module of a processor system, information of a recommendation associated with an application, information of the application, and information of a user of the application. The explanation generator module of the processor system is used to determine an explanation format of an explanation of the recommendation based at least in part on the information of the recommendation associated with the application, the information of the application, and the information of the user of the application.

Automatically generating personalized and context-aware explanation formats for a recommendation

A machine learning model can be run with a first input data to obtain a first output from the machine learning model. A first rule representing an interpretable explanation for the machine learning model predicting the first output can be obtained. A modified rule can be received, which changes the first rule. A transformation function can be generated, which transforms a given input data for inputting to the machine learning model to a new input data based on decision boundaries of the machine learning model and the modified rule. The first rule, the first output, the modified rule, and the transformation function can be stored in a first table.

Hybrid user contributed rules and machine learning framework

In a method for interpreting output of a machine learning model, a processor receives a first interpretable rule set. A processor may also receive a second interpretable rule set generated from a dataset and model-predicted labels classifying the dataset. A processor may also generate a difference metric and mapping between the first interpretable rule set and the second interpretable rule set.

Interpretable model changes

Machine learning model change management in an online Software as a Medical Device ('SaMD') is provided. One or more machine learning models implemented in a medical domain may be monitored where the one or more machine learning models are continuously updated. One or more changes to the one or more machine learning models. The one or more machine learning models, having the one or more changes, are certified as being in compliance with performance characteristics and compliance criteria.

Model change management of online software as a medical device

Embodiments are disclosed for a method. The method includes receiving feedback decision rules for multiple predictions by a trained machine learning model. generating a feedback rule set based on the feedback decision rules. The method further includes generating an updated training dataset based on an original training dataset and an updated feedback rule set. The updated feedback rule set resolves one or more conflicts of the feedback rule set, and the updated training dataset is configured to train the machine learning model to move a decision boundary. Generating the updated training dataset includes generating multiple updated training instances by applying one of the feedback decision rules to a training instance of the original training dataset.

Moving decision boundaries in machine learning models

Embodiments for recommending actions to improve machine learning predictions by a processor. One or more recommended actions may be linked to one or more features that influence a predicted outcome of a prediction model of a machine learning operation. One or more features having one or more negative factors that negatively impact the predicted outcome of the prediction model may be determined and selected. One or more of the linked recommended actions may be applied to one or more of the features to mitigate a negative impact upon the predicted outcome of the prediction model.

Linking actions to machine learning prediction explanations

Embodiments of the invention are directed to techniques that include predicting, by a computer system, a number of predicted opportunities and signatures of the predicted opportunities expected in a time window. Based on the signatures of the predicted opportunities, the computer system generates a listing of entities ranked according to signatures of the predicted opportunities. The computer system selects the entities to be assigned to the predicted opportunities based, at least in part, on computing capacity related to sales while accounting for any current opportunities having been assigned to the entities.

Predictive capacity optimizer

Embodiments for implementing intelligent automation of opportunity transaction workflows by a processor. One or more tasks identified in an existing transaction opportunity workflow suitable for automation may be automated in a current transaction opportunity workflow. The automated tasks may be scheduled and executed in the current transaction opportunity workflow. The automated tasks in the current transaction opportunity workflow may be monitored.

Intelligent automation of self service product identification and delivery

Aspects of the present disclosure relate to chat management to address queries. A query can be received. A determination can be made whether the query has already been answered by comparing the query to text within a chat database. In response to determining that the query has not been answered, a set of prospective experts can be identified. Each of the prospective experts of the set of prospective experts can be ranked based on at least one factor. The query can be transmitted to a first ranked expert. An answer to the query can then be received from the first ranked expert.

Chat management to address queries

Aspects of the invention include identifying each solution component of a plurality of solution components described in a text of a solution template of a plurality of solution templates, wherein the solution template includes a first combination of solution components. Identifying each solution component of a plurality of solution component described by an object in the solution template of a plurality of solution templates. Detecting a respective number of instances of each solution component in the solution template and a respective number of instances of each solution component in each other solution template of the plurality of solution templates. Generating analytics for a source company based on the respective number of instances of each solution component in the solution template and the respective number of instances of each solution component in each other solution template of the plurality of solution templates.

Facilitating information technology solution templates

Embodiments for implementing intelligent opportunity recommendation and management by a processor. A channel selection model mat be applied to a selected opportunity in view of a plurality of opportunity attributes to identify one or more team candidates of an entity or one or more entity partners ranked by alignment with the selected opportunity and determine a recommended opportunity owner from the one or more team candidates of the entity, the one or more entity partners, or a combination thereof.

Intelligent opportunity recommendation

Various embodiments are provided for providing intelligent dialog re-elicitation in a dialog system in a computing environment by a processor. Information, provided during a dialog using the dialog system, may be detected that has been subsequently revised. One or more variables impacted by the revised information provided during the dialog may be dynamically re-elicited.

Growing community of inventors

Dublin, Ireland

Massimiliano Mattetti