Varshith N | Machine Learning enthusiast

Varshith N

Machine Learning enthusiast

Based in BENGALURU

About

Enthusiastic about machine learning, I specialize in crafting intelligent solutions. Proficient in Python, Neural Networks, and Git, I showcase my expertise through interactive Streamlit applications. From data analysis to visualization, my portfolio is a glimpse into the fusion of innovation and technology.

Skills

Projects

Hand Written Digit Recognition - Web App

An interactive Streamlit web application with optimized Multi-Layer Perceptron model for hand written digit recognition.

Big-Cat-Image-Classification

This web application hosted on Streamlit is capable of classifying 4 class of Big Cats namely: Lion, Tiger, Cheetah & Leopard.

Dog-Breed-Object-detection

Implemented a comprehensive computer vision project focused on dog breed detection utilizing the state-of-the-art YOLOv8 model integrated with the Roboflow platform. The project aimed to accurately identify and classify dog breeds in images, demonstrating proficiency in deep learning and CV.

Sentiment Analysis using NLP

Conducted Sentiment Analysis using Natural Language Processing (NLP) to distinguish between positive and negative reviews for a movie. Implemented machine learning models to analyze textual data, enabling accurate sentiment classification for improved understanding of audience feedback.

Experience

2021

Web Developer Intern

Worked on a front-end project to develop a website to detect skin-tone. Key role played in integrating ML model into Django web application

Feb - Mar 2024

Data Analyst Intern

Prepare comprehensive reports and visualizations summarizing analysis findings, highlighting key performance indicators, and providing actionable recommendations to stakeholders using Python.

April 2024 – September 2025

Product Analyst Intern

• Built time-series KPIs & dashboards to monitor user behavior & business metrics across content & ad funnels. • Automated reporting workflows using BigQuery, Redash & Apps Script to streamline performance monitoring. • Developed SQL-based ETL pipelines to preprocess data from event logs and sensors for scalable reporting. • Led A/B testing and statistical analysis using hypothesis testing and confidence intervals to guide product decisions. • Defined analytics requirements with product & tech teams to improve data tracking for model experimentation. • Contributed to feature engineering pipelines supporting ML experimentation for product recommendations.

Education

2021-2024

M.Sc Data Analyics

Masters in Data Analytics at Christ University, Bengaluru

AI foundation: Neural Networks - Certification

Completed LinkedIn certification in "AI Foundation: Neural Networks," showcasing proficiency in fundamental concepts and applications of neural networks in artificial intelligence. Demonstrated knowledge in the design, training, and optimization of neural networks, establishing a strong foundation in the field of AI.

NLP with Python for ML

Earned a LinkedIn certification in "NLP with Python for ML," demonstrating expertise in Natural Language Processing techniques using Python for Machine Learning applications. Acquired skills in text preprocessing, sentiment analysis, and language modeling, showcasing practical knowledge in leveraging NLP for data-driven insights and solutions.

Applied ML: Feature Engineering

Attained a LinkedIn certification in "Applied ML: Feature Engineering," showcasing proficiency in the crucial aspect of enhancing machine learning models by strategically crafting and optimizing features. Demonstrated expertise in extracting valuable information from raw data, contributing to improved model performance and predictive accuracy.

Prompt Engineering - LinkedIn

Successfully completed the "Prompt Engineering" certification from LinkedIn, specializing in the design and optimization of prompts for natural language processing (NLP) and machine learning (ML) applications. This certification focused on advanced techniques for crafting effective and contextually relevant prompts to enhance model performance and interpretability in various NLP-driven projects.