• Subjects: Physics, Maths, Chemistry, Computer Science, and English
• Indian CBSE curriculum
• School House Captain (2014 - 2015)
• Subjects: Mathematics, Natural Sciences, Social Sciences, French and English.
Single-handedly contributed to creating and modifying pages using templates, content slots, and components.
Designed and modified email functionalities along with business processes.
Created Impex’s and cronjobs for scheduled tasks.
Modified an assigned module by writing controller classes, business logic at the service layer, and JSP pages, understanding end-to-end process.
Solitarily worked on client-reported defects to fix them punctually. Also, added bug fixes to the client's system.
Made configuration customization within Backoffice for reporting.
Assisted clients in the order management process, including sending orders to SAP.
• Learned technologies used within the company - Spring Boot and Java.
• Developing Rest API using Spring Boot and testing it using Postman API.
• Cracked the Advanced level software test.
• Worked on a project to develop a credit scoring model that would distinguish between good and bad loans.
• Performed univariate and bivariate analysis on a dataset containing loan data retrieved from the lending club website.
• Statistical techniques like Weight of Evidence (WOE) and Information Value (IV) were used to screen the variables.
• Developed a Python package that contains all the necessary functions required for performing EDA.
• Independently developed book Recommendation Engine based on Google Book API and parameterized equation scores to provide recommendations to any user.
• Utilized Amazon Rekognition and S3 bucket to create emotion-based-color changing bounding boxes around each video frame passed as input.
• Parallelly, developed a backend content-based recommendation engine using the Goodreads dataset.
Developed a hybrid machine learning model which can first predict the AQI based on certain levels of different chemical pollutants in the air and also classifies them by using a logistic regression technique or a passive-aggressive classifier model, with a final score of 58.16%.
Developed a web application using Flask Framework, along with transfer learning models such as Resnet50 and InceptionV3, for predicting whether the cotton plant's image illustrates that it is diseased or not.
Implemented N.L.P. applications with random forest classifier, Cat Boost classifier, and XG-Boost classifier models, with hyperparameter tuning, to predict whether the news headlines given as input will have a negative or positive impact on the stocks based on the closing index.
Developed a face recognition model to mark attendance using OpenCV and face-Recognition libraries of the known people by providing an image file of the user and matching them accordingly with the webcam.