Eric Kevin Butler - San Jose CA, US Ramani Ranjan Routray - San Jose CA, US Prasenjit Sarkar - San Jose CA, US Chung-hao Tan - San Jose CA, US Kiyoung Yang - San Diego CA, US
Assignee:
International Business Machines Corporation - Armonk NY
International Classification:
G06F 15/16 G06F 7/00
US Classification:
709224, 709226, 709228, 4554561, 382240
Abstract:
A method and system for automatically identifying an optimal set of attributes of entities included in a networked system. Entity types are ranked based on information gain. A first classification accuracy relative to a first entity type is determined. The first entity type is the top-ranked entity type or a first aggregate entity type. A second entity type is selected base on the ranking. A database join of a first set of attributes associated with the first entity type and a second set of attributes associated with the second entity type is performed. A second classification accuracy relative to a second aggregate entity type generated by the join is determined. In response to determining that the second classification accuracy is not greater than the first classification accuracy, an optimal set of attributes contributing to a problem in the networked system is identified as the first set of attributes.
Automatically Identifying An Optimal Set Of Attributes To Facilitate Generating Best Practices For Configuring A Networked System
Eric Kevin Butler - San Jose CA, US Ramani Ranjan Routray - San Jose CA, US Prasenjit Sarkar - San Jose CA, US Chung-hao Tan - San Jose CA, US Kiyoung Yang - San Diego CA, US
International Classification:
G06F 17/30
US Classification:
707 2, 707E17009
Abstract:
A method and system for automatically identifying an optimal set of attributes of entities included in a networked system. Entity types are ranked based on information gain. A first classification accuracy relative to a first entity type is determined. The first entity type is the top-ranked entity type or a first aggregate entity type. A second entity type is selected basal on the ranking. A database join of a first set of attributes associated with the first entity type and a second set of attributes associated with the second entity type is performed. A second classification accuracy relative to a second aggregate entity type generated by the join is determined. In response to determining that the second classification accuracy is not greater than the first classification accuracy, an optimal set of attributes contributing to a problem in the networked system is identified as the first set of attributes.
- San Jose CA, US Yuting Jia - San Diego CA, US Kiyoung Yang - San Diego CA, US Heming Xu - San Diego CA, US
International Classification:
G06N 99/00 G06F 3/0485 G06T 11/20
Abstract:
The current subject matter describes a method and system of detecting frauds or anomalous behavior. The procedures include extracting characteristics from a dataset to generate words and documents, executing a topic model to obtain the respective probabilities of appearance of a document in each latent archetype, dividing the dataset into a plurality of subsets based upon the archetypes. The formed subsets are further utilized to estimate the quantiles and calculate scores using a self-calibrating outlier model. The score of each new transaction is determined based on a single archetype or based on the sum of weighted scores determined from all the archetypes and associated statistics. Such methods are superior to a simple self-calibration outlier model without an LDA archetype. The detection system with the LDA archetypes and self-calibrating outlier model is implemented with the sliding window technique incorporating new transactions into the topic model and it is capable of operating in real-time for the purpose of identifying frauds and outliers.
Microsoft
Principal Data and Applied Scientist
Microsoft Jun 2016 - May 2019
Senior Data and Applied Scientist
Adeptra May 2007 - Jun 2016
Senior Scientist
University of Southern California Aug 2001 - May 2007
Research Assistant
Ibm Jun 2006 - Aug 2006
Research Intern
Education:
University of Southern California 2001 - 2007
Doctorates, Doctor of Philosophy, Computer Science
Korea Advanced Institute of Science and Technology 1992 - 1996
Bachelors, Bachelor of Science, Computer Science
Skills:
Machine Learning Data Mining Pattern Recognition Artificial Intelligence Neural Networks Big Data Predictive Analytics Statistical Modeling Predictive Modeling Analytics Perl C C++ R Java Python Information Retrieval Software Engineering Computer Science Optimization Apache Spark Data Analysis Linux Postgresql Sql Matlab Agile Methodologies Postgis Lda Oracle Database Git Subversion Rally Bitbucket Gnu Octave Jenkins
Languages:
English Korean
Certifications:
Oracle Certified Dba, Oracle 8I Ibm Certified Aix Administrator, Aix 4.X Oracle Ibm