VAISHNAVI GADDE

Melbourne, Australia· Email

Post-Graduate in Data Science.
I have demonstrated knowledge and experience in various stages of the Data Pipeline from data collection, wrangling, modelling, visualization and building machine learning models that can create disruptive business ideas.

Experience

Data Scientist

Monash University

Project: Safe Lungs At Work

  • Designed a web application with a team of 4 members that allows users of our website to record their situation through questionnaire and know if their lungs are being affected by the job, they do i.e. Does occupation of a person affect human lungs? Based on their answers we provide a customised solution to a user that could reduce their risk.
  • Designed ER model using open data sets and stored data at a backend using C sharp and that is stored on AWS server. This data has been used to provide a customised solution to a user.
  • Designed Infographics in the website after data cleansing open datasets to let the audience more clearer and easily understand the impact.
  • Used Professional tools like Lean kit, Slack for communication
  • Worked on Agile Methodology to release frequent, continuous website building and development

Aug 2020-Nov 2020

Business Consultant

Contemporary Arts Media
  • Led a diverse team of 5 international students to conduct an extensive analysis on art films produced by Contemporary Arts Media
  • Researched on how recommendation algorithms in art films of Contemporary Arts Media works and suggested better approaches that increase accuracy and effectiveness of their recommended suggestions.
  • Done a marketing research, strategic planning and management on devising business-level strategies and conducted online surveys of reaching to almost 7000+ libraries with diverse teams that finally ends up with suggestive measures to the company that increases their scope by meeting needs of customers.
Jul 2020

Research Data Analyst

Monash University

Project: Artificial Intelligence/ Machine Learning in Language Learning

  • Researched and analyzed the importance of language learning apps among different generations in the market.
  • Worked in a development team for developing an app for French language learning in automation tasks. For an example, if a teacher uploads an audio file, automating tasks like generating fill-in-the-blanks, parts of speech, drag and drop, pronunciation of words using Python which saved the time of teachers and developed my problem-solving skills.
  • Helped students who enrolled in Monash University for French learning course, to listen to the audios of French, which is uploaded by teachers with flexibility like slowing/increasing the audio depending upon their learning level, understand the meaning of each word in English for the respective French word, by utilizing Google API translator.
Jun 2019-Jul 2019 and
Nov 2019-Feb 2020

Cloud Developer

Tata Consultancy Services

Project: CEE6(Cloud Execution Environment), MCP(Mirantis Cloud Platform)

  • Worked under client Ericsson.Deployed CEE 6, MCP on Ericsson server along with implementing Openstack services to an end user
  • Implemented Python programmes via REST A.P.I calls for various components of Openstack (which is one of the cloud services), instead of utilizing those services by running commands via command line interface.
  • Troubleshooted and resolved various issues that were faced during the deployment phase in networking and for the proper functioning of Openstack and Kubernetes services, after the successful deployment.
  • Provided technical support to both internal and external clients by meeting the SLA’s.
Jul 2017-Jan 2019

Software Developer

Intern, Tata Consultancy Services

Project: OpenFlow Agent Management and Framework Development

  • Built SDN(Software Defined Network) using OpenFlow protocol by using Google built hardware and software along with a team of 4 members.
  • Troubleshooted various networking issues faced during the installation stage to final build of virtual topology of SDN.
  • Gained knowledge on various functional requirements required for the build of SDN like ODL (OpenDayLight), Mininet, Wireshark.
Dec 2016-May 2017

Education

Monash University, Melbourne

Masters, Data Science
  • Data Wrangling
  • Data Modelling
  • Data Exploration and Visualization
  • Machine Learning
  • Advanced Data Analytics
  • Data Processing for Big Data
  • Python Programming
  • DataBases
  • Business Information Systems
  • Industrial Experience
Mar 2019-Dec 2020

Jawaharlal Nehru Technology University, Kakinada

Bachelors, Computer Science and Engineering
  • Data Structures and Algorithms
  • Cloud Computing
  • Database Management Systems
  • Software Engineering
Oct 2013-May 2017

Skills

Projects

Text Classification and Topic Modelling of 3000 books

  • For Text-classification, abstract of 30000 books are taken as a train dataset and 5000 books are taken as test dataset and classified, to which category or content the book belongs too by building the model on train dataset.
  • For Topic-modelling, articles mentioned in Newspapers in the form of text has been taken and built the model to identify the articles that contain certain words.
  • Technologies Used: Python.
  • Packages Used: Pytorch, nltk, sklearn, pandas, gensim, numpy.
  • Machine Learning Algorithms: Neural networks, Logistic regression, BernoulliNB, LinearSVC, Randomforestclassifier, LDA.

Melbourne Housing Market

  • A Shiny application that allows users to explore the price of houses across various regions in Melbourne of different house types that include villas, town houses, likewise.
  • Allows users to explore the prices across various suburbs in Melbourne over the years, so that the buyers or sellers would get an idea of how the price of a house is being varied.
  • User of an app can select the price range in which they wanted to buy the house, so that the application shows in which regions, suburbs of Melbourne prices are present, what kind of houses are available in the selected range.
  • Technologies Used: R (Shiny), SQL, PowerBI.
  • Dataset: Obtained from kaggle.

Data Integration and Reshaping for Public Transport in Melbourne

  • After a proper integration of data from various files and transforming it into a readable format, given a location in Melbourne, I found what is the nearest railway station through which a person could travel and reach southern cross station in Melbourne within a short time.
  • From a user’s location, I found what are the nearest primary and secondary schools available.
  • Given a user’s location, I found what are the total number of crimes that have happened in that location.
  • Technologies Used: Python.
  • Packages Used: pandas, zip file, shapefile, difflib, re, shapely. geometry, sklearn, sklearn. linear_model, Beautifulsoup.
  • Dataset Used: Open dataset from Melbourne public transport.

Rain Prediction in Melbourne

  • Removed unwanted attributes of data-by-data cleansing and applied different machine learning algorithms to predict if there exists a rain tomorrow or not from previous records in the dataset and tested the accuracy of prediction.
  • Technologies Used: Pyspark.
  • Machine Learning Algorithms: Decision tree, Random forest, Support Vector Machine (SVM), Naive bayes, Logistic regression.
  • Dataset Used: Meteorology bureau of Melbourne.

Authorship Profiling on Twitter Data

  • By taking dataset of size 27000 tweets from Twitter and divided into train and test datasets. Later, I have built the models after proper pre-processing steps, to identify the gender of tweets.
  • Dataset: Obtained from Kaggle. This project was done as a part of Kaggle competition.
  • Machine Learning Algorithms: Logistic regression, Linear SVC, Random forest, Gradient boosting, Multinomial naive bayes.

Recommendation System on Retail Dataset

  • If a person goes to a retail shop to purchase items, I recommend him 10 items from the provided user-item list which is used as the train dataset and recommended 10 items for each user in the test dataset by building a recommendation algorithm.
  • Accuracy is checked across different built recommendations.
  • Technologies Used: Python.
  • Recommendation Algorithms: Collaborative filtering (implicit, bayesian, logistic), Matrix factorization.

Personal Accomplishments

  • Awarded Winter and Summer Research Scholarship in Monash University for the years 2019, 2020.
  • Participated in Kaggle in-class competitions in April, May 2020 and stood among the top 20% of participants.
  • Obtained 1967 Hackathons in Hacker Rank in Python Domain.
  • Awarded Prime Minister Scholarship for years 2013-2017.

Contact Me