* Designed an agent to fly a quadcopter, and then trained it using a reinforcement learning algorithm. * This project was part of Machine Learning - Advanced Nanodegree program at Udacity

* Built an algorithm to identify canine breed given an image of a dog. If given image of a human, the algorithm identifies a resembling dog breed. * This project was part of Machine Learning - Advanced Nanodegree program at Udacity.

* Reviewed unstructured data to understand the patterns and natural categories that the data fits into. Used multiple algorithms and both empirically and theoretically compared and contrasted their results. Made predictions about the natural categories of multiple types in a dataset, then checked these predictions against the result of unsupervised analysis. * This project was part of Machine Learning - Basics Nanodegree program at Udacity.

* Investigated factors that affect the likelihood of charity donations being made based on real census data. Developed a naive classifier to compare testing results to. Trained and tested several supervised machine learning models on preprocessed census data to predict the likelihood of donations. Selected the best model based on accuracy, a modified F-scoring metric, and algorithm efficiency. * This project was part of the Machine Learning - Basic Nanodegree program at Udacity.

Mentored summer trainees to develop business solutions related to Customer experience by applying Machine Learning and Natural Language Processing.

Build a machine learning model to classify customer feedback data into Technical or Non-Technical issues. And routed the feedback to the responsible teams accordingly.

Built an Anomaly detection unsupervised model for the response times of micro-services.

As part of the Innovation lab, I have worked on the Text-analytics use case to scrape data from Chinese e-commerce websites like Weibo, Taobao, JD, TMALL etc. And created a crawler in python to extract web data from the e-commerce website for sentimental analysis on the chinese texts.

Created a dynamic e-newsletter from scratch in the form of magazine with flip-page effects purely using Javascript , Jquey, HTML and CSS. Successfully launched four editions till now. The magazine and the effort of the team for building the e-newsletter was nominated for On-the-Spot award.

Wrote a Python script to scrape any twitter page using Selenium and BeautifulSoup (python lib).

A basic python Facebook-bot using Selenium that can automate birthday wishes to people/friends via crawling through one's Facebook birthday event page.

Created a website from scratch to display the data from the I-series DB2 on the UI using node.js. The UI part was built with HTML, CSS , Javascript and fetched the data from DB2 in the form of JSON using Ajax and Node.js. And the JSON data was displayed dynamically in tabular form on the UI.

Analyzing the effects of evolving cracks on cricket pitch using Image Processing and Machine Learning Algorithm to predict the favourability of pitch towards bowler/batsman under the guidance of Prof. Dr. Anand Gupta.

Remake of the single player 2048 puzzle game using JavaScript, HTML and CSS.

To computerize the maintenance of patient details and billing section in the hospital. This system has been developed to form whole management system including Doctors, Patients, and Bills etc. utilizing HTML and CSS as frontend, PHP and MYSQL as backend.

Developed a computer simulated "Hawk-Eye system in Cricket" (that have been used by host broadcasters in international tournaments) for the MS windows platform using Opengl under the guidance of professor Dr. Anand Gupta (NSIT), The objective of this project was to replicate a real world system on computer. The simulation uses OpenGL event handling mechanism to provide user input through mouse and keyboard.