Data Scientist

Resume posted by dataExplorer in Engineering.
Desired salary: $30.00
Desired position type: Any
Location: Bengaluru Karnataka, India

Contact dataExplorer


I’m a seasoned full stack developer with strong exposure in machine learning and nlp algorithms


ME Thesis:


Novel approach for Divide and Conquer K-Nearest Neighbour Classifier and its use in AdaBoost

  • Proposed a new classifier based on divide and conquer approach and use that classifier in the adaboost algorithm. Obtained results are reasonably good and are compared with the existing ones and the complexity of building the model is also low.



Course Projects at IISc:


  • Data Mining: Video Mining: object recognition in a given video stream
  • Topics in Combinatorial Geometry: Survey on Voronoi Diagrams and its applications.


Decision Resources Group (Sep 2015 to Present)

Data Analytics Team: Data Scientist

  • Working on Social Network Analysis of physian’s data to identify the right candidate to help clients promote their pharmaceutical business.
  • Genomic Data Exploration using spark framework.


Edgenetworks (Dec 2014 to Sep 2015)

Innovation Team: Data Scientist


  • Built skill repository for IT industry using textual data of job descriptions and resumes.


  • Built classifier for industries, domains across the verticals from companies data, job descriptions and resumes.
  • Building edgeGraph which provided intelligence to the internal products of EdgeNetworks.
  • Built a classifier to predict joining probability of a candidate in a company which made the offer.
  • Built a classifier to predict the leave probabilities of a candidate and a weekly report is sent to the client. 2014 to Dec 2014)


Batch Data Platform:


  • Built adhoc search tool over the raw data using elastic search.


  • Helped the analytics team in feature extraction, model tuning and deploying them in production. (March 2013 to Jan 2014) OE Solutions – Admin Console:


  • Automated the deployment feature for Predictive Experience Solutions which is used by service delivery team.


OE Solutions – Framework: (January 2012 to Feb 2013)


  • Involved in the design and development of client side framework of platform.


  • Introduced server side storage for Px-OE and migrated client side storage using




  • Involved in high priority production bugs.




Audio matching algorithms( September 2011 – December 2011)


  • Given a sample of 10 seconds audio file, identify the corresponding audio segments from huge corpus.




Akamai Technologies Solutions Pvt. Ltd., ( July-2009 to August-2011)



Team: Analytics Data Processing:


  • Involved in the design and development of the mapreduce framework.


  • Helped distribute a standalone system.


  • Implemented tools to monitor processing.


  • ML and NLP Algorithms
  • Python, Java, C
  • Hadoop, Spark
  • Cassandra, Mongo
  • Elastic Search
  • Linux



Groups & Associations