Welcome to my GitHub profile! Here you'll find a collection of projects that showcase my work across various domains, including software development, data science, and machine learning. Each section highlights different aspects of my projects, from academic diploma work to personal experiments and contributions to hackathons. Explore the repositories to see the diverse range of skills and innovations I've applied to real-world problems.
-
Sponsorship Coordination Platform Version 1
A sponsorship influencer coordination platform built with Flask and Bootstrap, designed to streamline the management of campaigns and offers between sponsors and influencers. Created as part of the MAD 1 project from IITM, this version includes secure authentication, campaign management, and data visualization with Matplotlib.
-
Sponsorship Coordination Platform Version 2
An enhanced version of the platform featuring a modern tech stack with Vue.js for the frontend and Flask for the backend. Developed for the MAD 2 project, it includes asynchronous task management with Celery and Redis for caching, offering an improved user interface and efficient background processing for campaign and offer management.
-
Restaurant Delivery Platforms Analysis BDM Project
This project analyzes restaurant delivery platforms to understand customer preferences, industry competition, and expansion opportunities. Conducted as part of the BDM project from IITM, it includes descriptive stats, distribution, correlation, regression, and geospatial analysis using multiple datasets.
-
"Recipe for Rating" predicts food ratings using machine learning. Developed for the IITM MLP project, it achieved a top score of 0.78288 (Version 16) and ranked 118 in a Kaggle competition. The dataset was highly biased with ratings of 1 and 2 at ~1.3% each, 0 and 4 at ~9.1% each, and 5 at 76.05%.
-
Predicting Hard Drive Failures attempts to tackle this problem via the use of different Machine Learning models. In this repo I have used various models for classifcation as well as regression, this is easily done via the use of PyCaret.
-
Mystery Maze is an exciting Java-based game developed during a game hackathon. Navigate through complex mazes, and uncover hidden secrets in a challenging single-player adventure. Download the game as an .exe for Windows or as a .jar for any platform with Java installed.
-
Walmart Workshop includes all the files utilized in the workshop. The workshop taught different methods for Time series forecasting, Supply Chain Optimization and Computer Vision. Walmart also held a hackathon, Round 1 of which is here and Round 2 is in the repo Predicting Drive Failure.
-
Arthropod Object Detection utilizes the capabilities of CNN to classify as well as idenify what arthropod is present in the image and where it is. The project is built using Tensorflow, and can be easily run on Kaggle.
-
Aspect Based Sentiment Analysis
Aspect Based Sentiment Analysis utilized Dependancy Parsing and prebuilt Sentiment Intensity Analyzer model from nltk to predict sentiment for different reviews. This helps in identfying what part of the review is positive and what part is negative. The data used is a Car Reviews Dataset.
-
Completed the Reinforcement Learning Specialization from Coursera in January 2024.
-
Artificial Intelligence and Edge Computing
Finished the Artificial Intelligence and Edge Computing course from L&T EduTech offered under BITS Pilani in December 2023.
-
Completed the IBM Cybersecurity Analyst Specialization from Coursera in Novermber 2023.
-
DeepLearning.AI Tensorflow Developer
Completed the DeepLearning.AI Tensorflow Developer Specialization from Coursera in October 2023.
-
Data Structures and Algorithms
Completed the Data Structures and Algorithms Specialization from Coursera in September 2023.
-
Finished the Machine Learning course by Andrew Ng on Coursera in June 2023.
To get started with any project, follow the instructions in the respective repository’s README file. Each project includes details on setup, dependencies, and usage.
Contributions are welcome! Feel free to fork the repositories, submit pull requests, or open issues to suggest improvements or report bugs.
All projects are licensed under the MIT License unless otherwise specified. See the LICENSE file in each repository for more details.