Arnav Saxena

London  +44 7444 465262   arnavsaxena1994@gmail.com  

Arnav is a Data Scientist based in London. He brings with him his capabilities in data science, data visualization, ETL and databases. He has a work experience of 2 years in Teradata and has completed his MSc in Data Science from the University of Sheffield. He has sound practical knowledge of Python, R, Tableau and the Hadoop ecosystem.


Experience

 September 2019 - Present

   Data Scientist


Currently Arnav is a part of various client and internal projects at Arup. He developed an industry first heat routing tool combining geospatial and energy sector insights using Python.
May 2019 - August 2019

   Data Science Intern


  • Responsible for creating an analytical table by merging multiple tables and data pre-processing. Used the analytical table for EDA and finding correlations amongst the variables. He compared different regression algorithms to predict the resale values (target variable) of vehicles and created insightful visualisations using Tableau. Furthermore, he used hyper-parameter tuning to optimise the model and attain accurate results.
  •  August 2016 - August 2018

       Jr. Data Scientist


    An American Multinational Sports Firm
  • Responsible for developing a data ingestion solution to capture web traffic data for different report suites in Spark environment.
  • Writing PySpark applications to parse raw data, populate staging tables and store the refined data in partitioned tables using hive.
  • Migration of current Java solution to Apache Spark using PySpark.
  • Development of Dynamic SQL for facilitating XML parsing and creation of logical functions in Python.

  • An American Retail Household Firm
  • Responsible for denormalising the existing web data for 6 report suites captured using Adobe Omniture.
  • Creating scripts in Unix to cleanse, transform and automate the data ingestion into HDFS.
  • Automating XML and hive DDL generation and validation using shell-scripting.
  • End-to-end testing of the solution.

  • An Indian Telecom Firm
  • Created a prediction model in python using random forest for complaint categorisation
  • Created valuable visual insights using Tableau.

  • An Asian Telecom firm
  • Developed and implemented models in R that predict Telecom Affinity and Churn for a large Asian Telecom firm.

  • Education

    University of Sheffield

    Masters of Science in Data Science
    Grade - Merit
    September 2018 - August 2019

    NMIMS University

    Bachelors of Technology in electronics and Telecommunication
    Grade 2:1
    August 2012 - May 2016

    Skills

    Programming Languages & Tools



    Interests

    I enjoy most of my time being outdoors, playing squash. I am an avid traveller and like to explore new places on foot.

    When forced indoors, I follow a number of sci-fi and fantasy genre movies and television shows, I am an aspiring chef, and I spend a large amount of my free time exploring the latest technology advancements in the Data Science realm.



    Certifications

    Trainings