Apr 2019
AWS Redshift Cluster Analysis
Extracted data from ZAGI database in PostgreSQL server, load into AWS S3, then Redshift using Python
Program: PostgreSQL, Python, S3, Redshift
I am a diligent researcher with a passion in data science, motivation in healthcare, and ambition in business. A B.S. in Biomedical Engineering from UAB and industrial research experience has geared me towards a data science career. I recently graduated with a M.S. in Data Science. On an average day, you will probably find me doing one, if not multiple, of the following: meeting clients for consulting projects, attending meetups, or participating in hackathons. Other than that, I enjoy exploring new cities, tasting new flavors and dishes from different cuisines, and watching an assortment of movies. I believe the best way to grow is to open the mind to learn and understand every part of the seen and unseen world. The key is to stay curious.
Email: p.ankur.715@gmail.com
Phone: 251-447-6255
Aug 2020 - current
Oct 2018 - Mar 2020
Sept 2019 - Feb 2020
Jun 2019 - Aug 2019
Jan 2019 - Feb 2019
May 2017 - Aug 2018
Aug 2016 - Dec 2016, Jan 2015 - May 2015
Group won first place for developing an Amazon Echo app to interact with customers to offer rewards and an option to donate for recycling ELC products, by using an infrared sensor and LED display to identify the item. The software used were Vision API, Cloud SQL, and Python.
Sep 2019
Group won 2nd place for developing a SaaS app called Seeker that uses Google Cloud Video Intelligence API for object detection and time intervals, and Yuuvis for storage and Search Service API to jump to time of searched object.
Apr 2019
The first routing app that provides the safest routes by using ArcGIS API and city wide traffic statistics. The app works by predicting the probability of vehicle crashes at a certain location given several inputs like precipitation chance and amount, temperature, time of day, past crashes, and sinuosity of the road.
Apr 2019
Competing against 6000 participants from 24 countries, team created an audio and image classification app to notify users of real-time and location-based crimes for evacuation and for lawyers’ use during claim cases.
Feb 2019
MobileAI phone app of image or video classification to assist visually impaired users in independent mobility through real-time navigation by capturing location from the pre-trained model.
Nov 2018
Birmingham, Alabama
Aug 2012 - May 2015
Jersey City, New Jersey
Sep 2018 - Feb 2020
Analyzed time-series data of stocks for stock returns, volatility calculations, OLS, back testing, predictive, along with quantopian research.
Python
Extracted data from ZAGI database in PostgreSQL server, load into AWS S3, then Redshift using Python
Program: PostgreSQL, Python, S3, Redshift
Employed machine learning, ensemble, and statistical analysis for feature selection and tuned models for predicting heart disease with 93% accuracy
Program: R
Analyzed tweets of 2020 Democratic Presidential Candidates from Apr 4-11 uniformly by state, and tweets from the candidates' personal Twitter accounts from Nov 1 - Mar 31
Program: R
Multilayer perceptron (feed forward neural network) with hidden layers on iris dataset; CNN for image classification in MNIST, SVHN, and pet dataset
Program: Python