Hi, I am Sayanti Das
Turning Data Into Insights, Ideas Into Impact.
I’m an aspiring Data Scientist passionate about transforming data into meaningful insights and building intelligent applications using Machine Learning, Deep Learning, NLP, and Generative AI.
I began my professional journey as a WordPress Developer, where I gained hands-on experience building responsive, user-friendly, and performance-focused websites.
My interest in technology gradually led me toward Data Science and Artificial Intelligence. I started exploring Python, data analysis, machine learning, deep learning, NLP
Today, I focus on developing practical projects that combine data analysis, predictive modeling, AI, and software development to solve real-world problems.
I’m currently looking for opportunities where I can apply my skills, learn from experienced professionals, and contribute to meaningful data-driven solutions.
B.Sc. in Biochemistry
Developed analytical thinking, scientific reasoning, and problem-solving skills.
Around 1 Year Professional Experience
Built responsive, performance-focused, and user-friendly websites.
Python • SQL • Pandas • NumPy
Started working with data analysis, visualization, and statistical concepts.
ML • Deep Learning • NLP • LLM
Currently building intelligent applications and solving real-world problems using AI.
Python
SQL
Pandas
NumPy
Exploratory
Matplotlib
Data Cleaning
Plotly
TensorFlow
Keras
Neural Networks
LSTM
Scikit-learn
Regression
Classification
Clustering
Feature Engineering
Model Evaluation
NLP
RAG
Embeddings
LLMS
FastAPI (Backend)
MongoDB
Git
GitHub
Vercel
Render
MongoDB An intelligent recruitment platform designed to analyze resumes, classify candidate profiles, extract relevant skills, and match candidates with job descriptions.
A full-stack inventory management system that combines data analytics and machine learning to manage products, suppliers, inventory while generating predictive insights.
Understand → Collect & Clean → Explore → Build → Evaluate → Deploy & Improve
Understand Understand the business problem, requirements, and objectives.
Collect & Clean Prepare the dataset by handling missing values, duplicates, inconsistencies, and irrelevant information.
Explore Perform exploratory data analysis to discover patterns, relationships, trends, and important features.
Build Select appropriate machine learning or deep learning algorithms and train predictive models.
Evaluate Evaluate model performance using suitable metrics and validate the results.
Deploy & Improve Convert the solution into a usable application and continuously improve its performance.