Inspired by 2018 disasters in Uttarakhand and Kerala. Remodeled a state-of-the-art algorithm, MaskRCNN, to detect humans in flood affected areas and to compute how well it works in Real-life situations (performance on video).
Developed a platform that consumed historical quotes data (via the Alphavantage API) and tweets (via Twitter’s API) and performed sentiment analysis using TextBlob. Stored data in MongoDB and exported to AWS S3. Then trained the SparkML model on this server and exposed it via a REST API, which was used to predict the future close price for a stock over a time interval, helping determine whether to buy or sell it.
Created visualization to show how Aid-data flows between countries using Temporal, Spatial and Network visualizations.
Developed a system that predicted whether a claim was to be accepted or not using classical ML algorithms and blockchain was used to keep data secure and distributed. It was made as a webapp using flask.
I am currently working as a software developer at Fastenal. In my free time, I love to play CSGO, watch matches of Chelsea FC and do photography. I also like to keep on top of any and all breaches, hacks, data dumps and new vulnerabilities specially targetting windows OS.
DISCLAIMER : Lists below will keep growing so make sure to revisit!
Code: [ Python, Java, d3.js, Javascript, HTML, CSS, KSQL, SQL, C++, Shell scripting ]
Tools and Tech: [ Kafka, Kafka Streams, AWS, Matplotlib, Numpy, OpenCV, Pandas, Pytorch, Sci-kit, Scipy, ServiceNow, SparkML, Splunk, Tableau, Tensorflow ]