Search

Alexander A Arsky

from Redmond, WA
Age ~63

Alexander Arsky Phones & Addresses

  • Redmond, WA
  • Menlo Park, CA
  • Cedar Park, TX
  • 225 Clark Ave, Los Altos, CA 94022
  • 2316 Alcalde St, Santa Clara, CA 95054
  • Greenbelt, MD
  • Sunnyvale, CA
  • Rockville, MD

Resumes

Resumes

Alexander Arsky Photo 1

Software Engineer

View page
Location:
Menlo Park, CA
Industry:
Internet
Work:
Google - Mountain View, CA since Nov 2010
Member of Technical Staff

Yahoo! Inc 2003 - 2009
Principal Researcher/Manager

Inktomi 1998 - 2003
Principal Search Engineer

Visigenic/Borland Sep 1997 - Oct 1998
Senior Member of Staff

Manugistics Feb 1994 - Sep 1997
Lead Software Engineer
Education:
Institute of Atmospheric Physics of Academy of Science, Moscow
PhD Studies, Geophysics and Numerical Climate Modelling
Moscow State University, Moscow
MS, Meteorology and Climate Modelling
Skills:
Information Retrieval
Algorithms
Distributed Systems
Scalability
Python
Search
Mapreduce
Big Data
Data Mining
Machine Learning
Hadoop
C++
Software Engineering
Search Engine
Java
Artificial Intelligence
Computer Science
Programming
Search Engines
Search Engine Technology
Software Development
Natural Language Processing
Text Mining
Recommender Systems
Large Scale Systems
Go
High Performance Computing
Languages:
Russian
English
Certifications:
Statistical Learning
Machine Learning
Natural Language Processing
Stanford University
Coursera
Deep Learning Specialization
Machine Learning (Link)
Natural Language Processing (Link)
Alexander Arsky Photo 2

Alexander Arsky

View page

Publications

Us Patents

Using Exceptional Changes In Webgraph Snapshots Over Time For Internet Entity Marking

View page
US Patent:
20070198603, Aug 23, 2007
Filed:
Feb 8, 2006
Appl. No.:
11/350967
Inventors:
Konstantinos Tsioutsiouliklis - San Jose CA, US
Bruce Smith - San Francisco CA, US
Dmitri Pavlovski - San Francisco CA, US
Alexander Arsky - Los Altos CA, US
International Classification:
G06F 17/30
US Classification:
707202000
Abstract:
Techniques are provided through which “suspicious” web pages may be identified automatically. A “suspicious” web page possesses characteristics that indicate some manipulation to artificially inflate the position of the web page within ranked search results. Web pages may be represented as nodes within a graph. Links between web pages may be represented as directed edges between the nodes. “Snapshots” of the current state of a network of interlinked web pages may be automatically generated at different times. In the time interval between snapshots, the state of the network may change. By comparing an earlier snapshot to a later snapshot, such changes can be identified. Extreme changes, which are deemed to vary significantly from the normal range of expected changes, can be detected automatically. Web pages relative to which these extreme changes have occurred may be marked as suspicious web pages which may merit further investigation or action.

Consecutive Crawling To Identify Transient Links

View page
US Patent:
20070226206, Sep 27, 2007
Filed:
Mar 23, 2006
Appl. No.:
11/388681
Inventors:
Dmitri Pavlovski - San Francisco CA, US
Vladimir Ofitserov - Foster City CA, US
Alexander Arsky - Los Altos CA, US
International Classification:
G06F 17/30
US Classification:
707005000
Abstract:
According to the approach described herein, an approach is provided for identifying transient links on a Web page by crawling a Web page consecutively after a brief interval and comparing the links from each crawl to identify transient links. The approach ensures that transient links are not crawled and archived, thereby saving resources for crawling valid links leading to useful information
Alexander A Arsky from Redmond, WA, age ~63 Get Report