Viveksinh Solanki

I am pursuing master's in Computer Science at Stevens Institute Of Technology. My major interest is in making machines understand human language.

I did my undergraduation from L.D. College Of Engineering, Ahmedabad with a major in Computer Engineering.

Actively seeking for full time position in Data Science/NLP from June 2020.

Email  /  Resume  /  LinkedIn  /  Github  /  Twitter

Eiffo Logo

Eiffo Analytics, New York, USA
Data Science Intern June 2019 - August 2019

  • Developed automated data preprocessing module for time series data
  • Designed automated time series forecasting system by utilizing Support Vector Machines, Linear Regression, XGBoost, LSTM and multilayer perceptron

Linaven Logo

Linaven Agency, Cannes, France (Remote Work)
Lead Android Developer July 2017 - May 2018

  • Developed an android application for French youtuber, which allowed the users to read all social media feeds of that French youtuber
  • Developed a social media application for french salsa community including dancers, DJs and general public

DISQ logo

Digital Impact Square, An Initiative by TCS Foundation, Nashik, India
Software Analyst July 2016 - June 2017

  • Developed a hybrid/cross-platform application using PhoneGap/Cordova framework as well as designed web dashboard to show visualizations of collected data
  • Developed a bilingual android platform to aid health workers in monitoring and tracking the health status of new mothers
  • Delivered technical training for our platform to 600+ health workers


Fake News Detection: Using An Ensemble Approach
Viveksinh Solanki Spring 2019

  • Applied support vector machine(SVM), multinomial naive bayes and convolutional neural network(CNN) individually on publicly available fake news datasets
  • Also applied the ensemble of SVM, MultinomialNB and CNN on the same datasets and compared the results


Automated Fake News Detection
Viveksinh Solanki, Akshay Rane, Ronald Fernandes, Gaurang Patel Spring 2019

  • Created dataset by scraping fake data from fake news sites and real data from mainstream news agency The NewYorkTimes
  • Performed iterative data cleaning, preprocessing and analysis to remove bias from the collected data
  • Performed Exploratory Data Analysis to get insights on the problem
  • Extracted top features using Random Forest feature importance
  • For modelling, utilized SVM, MultinomialNB and CNN


Labor Condition Application (LCA) approval prediction
Viveksinh Solanki, Saumya Shastri, Gaurang Patel, Ronald Fernandes Spring 2019

  • Performed data cleaning, preprocessing and feature extraction
  • Applied Random Forest, Multinomial NB, kNN, multilayer perceptron and SVM to predict the status (certified or denied) of LCA
  • Identified the best features/variables which can help in approval of LCA


Factors that might cause labor condition application (LCA) to be approved
Viveksinh Solanki, Vardaan Kishore Kumar Fall 2018

  • Applied Rubin Causal Model on H1B dataset to find causes that might help in LCA approval


Cheating'Quine, An Ad-hoc OLAP query processing engine
Viveksinh Solanki Fall 2018

Page design credits to awesome Jon Barron!