Data Science Professional with 7+ years of experience, holding a Postgraduate degree in Data Science & Business Analytics from Austin Texas University, and a Bachelor's in Electronics and Communication Engineering. Certified in Microsoft Azure Generative AI (Great Learning) and completed an ML internship at WorldQuant University. Proficient in leading ML and Generative AI projects, with deep expertise in engineering data analytics. Skilled at deriving actionable insights from complex datasets, with a strong focus on innovation and continuous improvement. Eager to apply my skills in a dynamic, forward-thinking Data Science role.
TOOLS: Tableau, MySQL, KNIME, Excel, DockerIDE: Jupyter Notebook, Google Colab, PyCharmMachine Learning: Classification, Regression, Linear & Logistic Regression, Decision Trees, Random Forest, NLP, Boosting & BaggingStatistical Methods: T-test, Chi-Square, PCA, Hypothesis Testing, ANOVAMETHODS: Data Wrangling, Missing & Outlier Treatment, Univariate & Bi-Variate Analysis, Bootstrap & Cross-ValidationAPI Development: FastAPI, Flask, StreamlitCloud Platforms: Microsoft Azure, AWS SageMakerVersion Control: Git/GitHubDeployment: Docker, AWS Lambda, Azure FunctionsGenerative AI & Prompt Engineering: RAG-based systems, summarization tasks with LLaMA, GPT, Mistral
Conducted an experiment to determine if sending reminder emails to applicants increases the likelihood of completing the admission exam.
Skills & Tools: Chi-Square Test, Odds Ratio, CDF, ETL, MongoDB, Exploratory Data Analysis (EDA)
Developed a GARCH time series model to predict asset volatility. Acquired stock data via API, performed data cleaning, stored it in a SQLite database, and built an API to serve real-time model predictions.
Skills & Tools: GARCH Model, SQL, REST API, Walk Forward Validation (WFV), ACF & PACF Plots
Skills & Tools: Linear Regression, Decision Tree, Random Forest, Boosting Techniques, EDA
Skills & Tools: Clustering, PCA, Data Mining, K-Nearest Neighbors, Decision Tree
Developed a chatbot using a Retrieval-Augmented Generation system for accurate document retrieval and response generation.
Technologies: Mistral -Nemo, Streamlit
Built a tool for summarizing PDFs and Word documents using fine-tuned LLMs to generate concise summaries.
Technologies: LLaMA, PyTorch.
Developed an automated report generator to extract business insights from datasets using fine-tuned LLMs.
Technologies: LLaMA, Tableau, Excel.
Built a sentiment analysis and summarization tool for customer reviews, providing actionable insights.
Technologies: GPT, NLTK.
Applied Data Science Lab, Machine Learning - (World Quant University)
GenAi Microsoft Azure - (Great Learning)
Applied Data Science Lab, Machine Learning - (World Quant University)