Kalyani Sonewane

Data Science and AI/ML Intern with a solid foundation in Python and machine learning. Proficient in SQL and NoSQL databases, and experienced in deep learning and natural language processing. Demonstrates hands-on expertise from a 9+ months internship, eager to leverage acquired skills to address real-world data challenges and contribute to impactful solutions.

1.Ride-Hailing price prediction based on weather condition:

To develop an ML model that can accurately predict ride-hailing prices based on weather conditions. The model will use historical data on ride-hailing prices and weather conditions to train and validate the model.

2. Supermart sales forecasting: 

To build Machine-learning model that can accurately predict the sales of each product in each store, which can help the company optimize its inventory management and marketing strategies to improve its sales and profitability.

 3.Social media sentiment Analysis with Root Cause analysis: 

The goal of this project is to develop a sentiment analysis system that can accurately determine the sentiment (positive, negative, or neutral) expressed in text data, and identify the root causes behind the sentiments. The system should be able to analyze large volumes of textual data from various sources, such as social media, customer reviews. 

4.Real-time Video-Audio Transcription & Summarizations :

A scalable and efficient real-time transcription and summarization system.

5.Object detection using LLM Model:

Developed an object detection system using Large Language Models (LLMs) to enhance image classification accuracy by integrating advanced contextual understanding with deep learning techniques. Achieved significant improvements in identifying and categorizing objects in complex scenes.

6. Created Chatbot using RAG:

Developed a chatbot using a Retrieval-Augmented Generation (RAG) approach, which integrates a knowledge retrieval system with a generative model to provide accurate and contextually relevant responses. The chatbot dynamically retrieves pertinent information from a vast dataset before generating answers, ensuring that users receive up-to-date and precise responses.

7.Created Chatbot using GROQ:

Created a chatbot using a Graph Recurrent Optimization Query (GROQ) framework, which leverages graph-based data structures and recurrent optimization techniques to enhance the accuracy and relevance of responses. This approach allows the chatbot to efficiently navigate complex data relationships and provide contextually enriched answers to user queries.