Machine Learning Portfolio
DataScientist.
I build end-to-end ML systems from data to deployment.
Focus: NLP, LLMs, FastAPI, Docker, and real-world use cases.
Tech Stack
Python
PyTorch
scikit-learn
FastAPI
Docker
Aryan Mishra
Professional Narrative
About Me.
B.Tech CSE (Data Science) · 2023-2027
I am a B.Tech CSE (Data Science) student at IIST Indore, building practical ML systems from analysis to API deployment.
My focus is NLP, LLM workflows, and reproducible pipelines. Open to internships and collaborative ML projects.
Currently Working On
→ Predicting Irrigation Need (Kaggle)
→ LLM Fine-tuning and MLOps Tooling
Open to Internships
IIST · 2027
Indore, India
Tech Stack
[ML / AI]
PyTorch
scikit-learn
LangChain
XGBoost
[Depl_Env]
FastAPI
Docker
PostgreSQL
GitHub Actions
Technical Skills
Core Skills.
Focused and Practical Stack
ML & AI
PyTorch
scikit-learn
LangChain
XGBoost
NLP
LLM Fine-tuning
Data & Infra
Python
Pandas / NumPy
FastAPI
Docker
Kubernetes
Tools & Ops
Git & GitHub
MLflow
GitHub Actions
Terraform
Selected Projects
Featured Projects.
31 Total Repositories
01
MLOps
↑ High Accuracy
Healthcare Risk Prediction
ML pipeline for diabetes, heart disease, and cancer risk prediction.
Approach
Built with scikit-learn and deployed via FastAPI with Docker.
scikit-learn
FastAPI
Docker
02
NLP
↑ 92.4% F1
LLM Fine-tuning Pipeline
Domain-specific fine-tuning of large language models.
Approach
Fine-tuned LLM using PyTorch and LangChain, tracked with MLflow.
PyTorch
LangChain
MLflow
03
Kaggle
Top 6.4%
March ML Mania 2026
Predicting outcomes for the NCAA basketball tournament.
Approach
Engineered features with Pandas and trained XGBoost models.
XGBoost
Pandas
04
Data
1M+ Rows
Predicting Irrigation Need
Kaggle competition dataset analysis and modeling.
Approach
Data cleaning, EDA, and feature engineering for agriculture.
Python
EDA
05
NLP
Fast
Text Summarization API
FastAPI backend serving an NLP summarization model.
Approach
HuggingFace transformers deployed behind a REST API.
HuggingFace
FastAPI
Competitive ML
Kaggle Profile.
Top Highlights
Datasets
Master
Ranked 120 of 9,783 globally
🥇 1 · 🥈 6 · 🥉 1
Notebooks
Expert
Ranked 1,598 of 62,266 globally
🥉 6
Published Datasets (Top 3)
39 votes
Cyber Attacks: Financial & Market Impact
45 votes
Tech Hiring & Layoffs: Workforce Data (2000–2025)
31 votes
Remote Work Burnout & Social Isolation (2026)
Competitions
March ML Mania 2026
Top 6.4% · 🥉 Bronze
#1#3,462
Learning and Certifications
Certifications & Awards.
Dec 2025
Applications of AI for Anomaly Detection
NVIDIA · Certificate of Competency
Apr 2026
March Machine Learning Mania 2026
Kaggle · Bronze Medal
Dec 2025
Data Visualization
Kaggle · Course Completion
Dec 2024
Intro to Machine Learning
Kaggle · Course Completion
Dec 2024
Intro to Programming
Kaggle · Course Completion
2024
Django Skill Up
GeeksforGeeks · Nation SkillUp
Oct 2024
Workshop on Algebraic Graph Theory
IIT Indore · SERB India
Jul–Oct 2023
C / C++ Programming Training
CodeMantra · ISO 9001:2015
Academic Record
Education Log.
2023 –
2027
Current
Indore Institute of Science and Technology
B.Tech CSE · Data Science Specialization
Focus: Machine Learning, NLP, and Data Engineering.
2020 –
2021
Previous
Rose Petal Higher Secondary School
Class XII · Science (PCM + Biology) · Rewa, Madhya Pradesh
2018 –
2019
School
Gyanasthali Sr. Secondary School
Class X · General Studies · Rewa, Madhya Pradesh
