Download PDF

EXPERIENCE

Oct 2016Present

Machine Learning Engineer

Xoriant Solutions

As the part of the R&D team, I develop and implement solutions in the domains of Machine Learning. I have worked on projects for clients that include the leading consulting companies, and multinational banks of the world. Some notable projects are listed below. 

  • Risk Analysis
    • Banks receive millions of documents for violating terms. Determining whether or not the text is pertinent requires one to read it in completion, this platform aims to ameliorate this problem by evaluating the document for possible risks and violations and predicting the extent of the potential loss for the bank.
    • Bidirectional Long Short Term Memory Network, Word Embedding, and Convolutional Neural Network were used to classify the text for risk with a precision of 92% and an accuracy of 88%.
    • On classification of a risk, an Extremely Randomized Trees classifier was used to predict the extent of risk (Very risky to less risky) hence enabling the bank to address the most relevant issues first. 
    • Technology stack: Python, Keras, NLTK, D3JS. 
  • Brand Sentiment Analysis
    • The BSA platform helps companies to determine the success of their products in the market based on sentiment analysis on empirical and live stream data from sources like Twitter, Facebook, News portals, and other sources giving critical insights into how the end customer feels about the product. 
    • Bagged model with Naive Bayes, Max Entropy, and Multilayered Perceptron was trained with an accuracy of 83%
    • Technology stack: Python, Flask, Sklearn, PyEnchant, GEvent, SocketIO, D3JS. 
  • Invoice Filter
    • Extracting the required fields from scanned invoices is a challenging and tedious task, Invoice Filter aims to solve it. 
    • Pre-processing was expedited using Cython. Image processing techniques like Binarisation, Deskewing, Rescaling were achieved using OpenCV, and ImageMagick. Finally, a custom Tesseract model was trained for the OCR task. 
    • Technology stack: Python, Cython, Flask, NLTK, OpenCV, Tesseract.
Jun 2016Jun 2016

Research and Development Intern

Indian Institute of Technology, Bombay
  • Implemented various APIs in existing infrastructure and designed a Recommender System with Restricted Boltzmann Machine.
  • Technology Stack: Java, Spring, Hibernate, and Python.
Apr 2016Jun 2016

Full Stack Developer Intern

Gig It!
  • Designed and implemented the front and back end of the company's official website.
  • Technology stack: Django/Python, Memcached, Nginx, CSS, HTML, JavaScript. 

SKILLS

  • Primary:                             Java (Weka, DL4J), Python (Sklearn, Cython, Keras, NLTK, TensorFlow, Matplotlib, Torch)
  • Proficient:                         C/C++, R, MATLAB, Django, Flask, Julia, LaTeX. 
  • Working Knowledge:   HTML, CSS, JavaScript, Spring, Hibernate, D3JS

EDUCATION

Jun 2012Jun 2016

Bachelors of Engineering, Information Technology; 76%; 8th rank in institution.

Smt. Kashibai Navale College of Engineering, University of Pune
Jun 2010Jun 2012

Higher Secondary; 70%

Chate College of Science, Pune
Jun 2000Jun 2010

Secondary; 84%

Bharati Vidyapeeth English Medium School, Pune

RESEARCH INTERESTS

I have immense interest in the domains of Machine Learning. Specifically, my research interests include the application of Deep Learning to Natural Language Processing, Computer Vision, and Reinforcement Learning. 

PROJECTS

Undergraduate Senior Year Project: Malfunction prediction

  • Atmega Microcontroller with pressure, light, temperature sensors were used to capture ambiance values.
  • Naive Bayes to predict malfunction of electronic appliances like Refrigerators, Air Conditioners, and Room Lights.

Undergraduate Senior Year Project II: Smart E-mail System

  • Text email classification in spam/ham using Support Vector Machine and RBF Kernel.
  • Automatic classification of emails in specific folders using Latent Dirichlet Allocation.

Linux Operating System                                                                                                                              

  • Compiled a working Linux Operating System using various open source packages.
  • Modified the Red-Black Tree implementation in the CFS scheduler with Priority Heap. 

Open Source: Scikit-Learn Project and NLTK

  • Scikit-learn and NLTK are the most popular open source Machine Learning libraries in Python. 
  • I am an active contributor to  both the projects. My contributions include bug fixes,  maintenance, and algorithmic improvements. 

HOBBIES

  • Competitive Programming
    • Ranked 99.99th percentile on HackerRank amongst one million users. 
    • Ranked 43/2000 on HackerEarth Codigo Mistreo 2.
    • Completed Google Foobar challenge.

  • Music

I have been playing Guitar for ten years, and Piano for three years. I have also played guitar professionally and recorded an album with my rock band Space