17974892. EVALUATING MACHINE LEARNING ON REMOTE DATASETS USING CONFIDENTIALITY-PRESERVING EVALUATION DATA simplified abstract (SAP SE)

From WikiPatents
Jump to navigation Jump to search

EVALUATING MACHINE LEARNING ON REMOTE DATASETS USING CONFIDENTIALITY-PRESERVING EVALUATION DATA

Organization Name

SAP SE

Inventor(s)

Philipp Knuesel of Nussloch (DE)

EVALUATING MACHINE LEARNING ON REMOTE DATASETS USING CONFIDENTIALITY-PRESERVING EVALUATION DATA - A simplified explanation of the abstract

This abstract first appeared for US patent application 17974892 titled 'EVALUATING MACHINE LEARNING ON REMOTE DATASETS USING CONFIDENTIALITY-PRESERVING EVALUATION DATA

Simplified Explanation

The present disclosure involves systems, software, and computer implemented methods for evaluating machine learning on remote datasets using confidentiality-preserving evaluation data.

  • Evaluation of machine learning on remote datasets using confidentiality-preserving evaluation data
  • Generating feature data for machine learning pipeline
  • Training baseline models and machine learning models on remote customer dataset
  • Generating aggregate evaluation data for models
  • Providing aggregate evaluation data to software provider

Potential Applications

This technology can be applied in various industries such as healthcare, finance, and e-commerce for evaluating machine learning models on remote datasets while preserving data confidentiality.

Problems Solved

1. Ensuring data confidentiality while evaluating machine learning models on remote datasets. 2. Streamlining the process of training and evaluating machine learning models for remote customers.

Benefits

1. Improved data security and confidentiality. 2. Efficient evaluation of machine learning models on remote datasets. 3. Enhanced collaboration between remote customers and software providers.

Potential Commercial Applications

Optimizing machine learning models for personalized healthcare recommendations in the healthcare industry.

Possible Prior Art

Prior art may include similar systems and methods for evaluating machine learning models on remote datasets while preserving data confidentiality.

Unanswered Questions

How does this technology ensure the confidentiality of evaluation data?

The technology uses confidentiality-preserving evaluation data techniques to ensure that sensitive information is not exposed during the evaluation process.

What are the specific machine learning libraries used in the remote customer database?

The abstract mentions the use of a machine learning library included in the remote customer database, but does not specify the exact libraries utilized.


Original Abstract Submitted

The present disclosure involves systems, software, and computer implemented methods for evaluating machine learning on remote datasets using confidentiality-preserving evaluation data. In response to determining that data of the remote customer dataset is of sufficient quality and quantity, feature data corresponding to a machine learning pipeline is generated. The remote customer dataset into one or more data partitions and for each partition, one or more baseline models and one or more machine learning models are trained using a machine learning library included in the remote customer database. Aggregate evaluation data is generated for each baseline model and each machine learning model that includes model debrief data and customer data statistics. In response to determining that the customer has enabled sharing of the aggregate evaluation data with a software provider who provided the remote customer database, the aggregate evaluation data is provided to the software provider.

Retrieved from "http://wikipatents.org/index.php?title=17974892._EVALUATING_MACHINE_LEARNING_ON_REMOTE_DATASETS_USING_CONFIDENTIALITY-PRESERVING_EVALUATION_DATA_simplified_abstract_(SAP_SE)&oldid=44638"