International Business Machines Corporation

Pankaj Srivastava

Dong Sheng Li

Stephen Mingyu Chu

Rahul Nahar

Tomomi Yoshioka

Michael Peran

Daniel Augenstern

Josh Price

Tobias Enders

Junichi Yan

Embodiments of the present disclosure include a computer-implemented method and system for determining when to retrain an individual-item model within a recommendation engine. The computer-implemented method includes defining a consumer feature vector having attributes of historical consumers that impact an individual-item model. The computer-implemented method further includes calculating a historical feature vector relating to the historical consumers. The computer-implemented method also includes determining a retraining threshold for the individual-item model and calculating a new feature vector relating to new consumers. The new feature vector containing new attribute values of the new consumers and defined by the consumer feature vector. The computer-implemented method further includes determining a distance between the historical feature vector and the new feature vector and retraining the individual-item model upon determining that the distance between the historical feature vector and the new feature vector exceeds the retraining threshold.

Retraining individual-item models

Techniques are provided for providing a local computation service on client device authorized by a remote service provider while keeping local data private from the remote service provider. In one example, a computer-implemented method comprises transmitting, by a device operatively coupled to a processor, a homomorphic encryption public key and homomorphically encrypted input data to a service provider. The computer-implemented method also comprises receiving, by the device from the service provider, a homomorphically encrypted signature generated based on the homomorphic encryption public key, the homomorphically encrypted input data, and a homomorphic encryption equivalent defined function. The computer-implemented method also comprises in response to a determination, based on a defined function corresponding to the homomorphic encryption equivalent defined function, that the homomorphically encrypted signature and input data corresponding to the homomorphically encrypted input data are valid for a computation service, performing, by the device, the computation service on the input data.

Providing computation services with privacy

Growing community of inventors

Bedford, NY, United States of America

Pankaj Srivastava