Shrishti B.

Aspiring Data Scientist | NLP Projects | Python | Machine Learning

Raipur, IndiaArtificial Intelligence and Machine Learning
2roles
51skills
3education
2credentials

About

🌟 About Me 🌟 I'm Shrishti Banshiar, a passionate and driven student currently pursuing the IITM BS degree, specializing in foundational concepts that form the bedrock of the tech and data science fields. My academic journey has equipped me with hands-on experience in a diverse range of projects, from T20 Cricket Data Analysis and Probability Theory to Corporate Bond Credit Rating Analysis. 💡 What I Bring to the Table Programming & Data Analysis: Proficient in Python, with expertise in data manipulation, statistical analysis, and algorithmic problem-solving. Machine Learning Projects: Successfully developed models for Iris Flower Classification and House Price Prediction, demonstrating my skills in both classification and regression tasks. Quantitative Research: Deep interest in understanding data-driven patterns, utilizing concepts like covariance, Chebyshev's inequality, and regression metrics. Academic Achievements: Excelled in coursework, emphasizing the practical application of mathematical and analytical skills. ✨ Achievements & Work Ethic I'm currently balancing an internship where I'm tackling both minor and major projects, which has refined my skills in project management, data visualization, and communication. My commitment to excellence ensures I approach each task with diligence and creativity. 📈 Career Aspirations I aspire to make a mark in the fields of data science and machine learning, with a keen interest in leveraging technology to create meaningful impact and drive decision-making processes. I'm always eager to learn, grow, and collaborate on innovative projects. Let's connect and discuss how we can learn from each other or collaborate on exciting opportunities!

Experience

Google Summer of Code Contributor

IIT Madras / Open Source

2025 · Remote

Selected as a Google Summer of Code 2025 contributor; built open-source AI/data tooling, designed data pipeline components, and implemented AI tooling integrations.

AI/Data Science Collaborator

Contract Project

2024 · Remote

Built ML-powered data tools and automated data pipelines integrating third-party APIs; delivered interactive dashboards and model insights for data-driven decision making.

Education

Indian Institute of Technology, Madras

Bachelor of Science, Data Science

[object Object]

Holy Cross Byron Bazar

[object Object]

Indian Institute of Technology (IIT) Madras

B.S., Data Science, Machine Learning & AI

2023 – 2027

Skills

SeleniumPandas (Software)Embedded JavaScript (EJS)MySQLPython (Programming Language)Microsoft OfficeAnalytical SkillsReliabilityProblem SolvingBusiness InsightsStreamsIdentifying TrendsData StructuresData CleaningModel ValidationDashboard MetricsEnd-to-End Project ManagementProject ManagementEDAData ScrapingLinux ToolsWeb ApplicationsLogistic RegressionNumPyWeb ScrapingMatplotlibIn Vitro Fertilization (IVF)Data ScienceData CollectionPythonJavaScriptTypeScriptSQLJavaScikit-learnNLTKTF-IDFNLP PipelinesWeb Speech APIREST AI APIsNext.jsReactFastAPIFlaskStreamlitNextAuthOAuthGitREST APIsPower BIDocker

Projects

HOUSE PRICE PREDICTION

The House Price Prediction project aims to develop a regression model to predict house prices based on various features such as location, size, and other relevant characteristics. Using a dataset (e.g., Boston Housing or Kaggle House Prices dataset), we applied data preprocessing, built a Linear Regression model, and evaluated its performance using metrics like Mean Squared Error (MSE) and R squared. Visualisations, including a correlation heatmap and residual plots, provided insights into feature relationships and model accuracy. The project highlights potential improvements, such as testing more advanced algorithms and refining data preprocessing, to achieve better prediction accuracy.

IRIS FLOWER CLASSIFICATION ANALYSIS

The Iris Classification project aims to classify iris flowers into three species—Setosa, Versicolor, and Virginica—based on their physical characteristics (sepal and petal length and width). The project utilizes machine learning techniques, specifically the K-Nearest Neighbors (KNN) algorithm, to predict the species of iris flowers based on given measurements.

AnalystGPT — AI-Powered Data Analysis Platform

Production-ready AI SaaS platform using Next.js and FastAPI for real-time analysis of user-uploaded datasets. Includes voice-to-query input with Web Speech API, OpenAI-compatible endpoint integration, authentication with NextAuth and JWT, dynamic chart generation, PDF export, pinned dashboards, ML predictions, and dataset cleaning and comparison.

Fake News Detector

End-to-end NLP pipeline using NLTK preprocessing, TF-IDF vectorization, and Logistic Regression classification, integrated with a real-time News API and deployed as a Streamlit application.

Judgment Bias Detector

NLP-based tool for detecting bias patterns in court judgments using text preprocessing and classification, with a Streamlit dashboard and bias visualizations.

Court Data Fetcher & Mini Dashboard

Automated web scraper and Flask dashboard for real-time court case data with CSV/SQLite storage, PDF export, external API integration, and automated data pipelines.