Built an AI-powered chatbot to assist students with campus-related queries, streamlining communication.
CampusAssist is an AI-powered chatbot designed to assist students with campus-related queries, including information about courses, faculty, event schedules, and general campus facilities. Developed using Python, the chatbot leverages Natural Language Processing (NLP) techniques to understand and respond to user inquiries. Harsh integrated the chatbot with an easy-to-use user interface, allowing students to engage in real-time conversations through a simple chat interface. The system I was trained on various frequently asked questions and topics related to campus life, making it capable of providing instant and relevant responses. Harsh implemented NLP algorithms using libraries such as NLTK and spaCy to ensure that the chatbot can handle a wide range of student queries, from course-related inquiries to event updates. One of the key features of the chatbot is its ability to learn from interactions, adapting its responses to improve accuracy over time. This capability is achieved through machine learning models that continuously optimize the chatbotβs performance based on user feedback. Additionally, the chatbot can integrate with the campus information systems to fetch live data, such as course availability, event schedules, and faculty office hours. By providing immediate, automated assistance, the chatbot reduces the workload on campus administration and enhances the overall student experience. The project offered Harsh the opportunity to explore the application of artificial intelligence in real-world problem-solving, improving operational efficiency while providing students with timely information.
Digital Creator & Problem Solver
@harshgarg-1Built a trend prediction model for retail market forecasting using machine learning and real-time data.
Developed a machine learning-based recommendation system for retail personalization using AWS and Python.
Designed a data-driven hiring strategy, cutting time-to-hire by 30%.