Fresher

Pooja Ganesh Mohite

898-***-**** LinkedIn Github **************@*****.***

Aspiring AI/Data Science Engineer with hands-on experience in machine learning, NLP, time-series forecasting, and financial data analytics.

Skilled in building end-to-end data pipelines, predictive models, and AI-powered applications using Python, TensorFlow, and Streamlit.

Currently exploring Large Language Models (LLMs), embeddings, and Retrieval-Augmented Generation (RAG) systems for intelligent

document analysis. Passionate about developing scalable AI solutions and contributing to production-grade machine learning workflows.

PROJECTS

Stock Price Forecasting & Financial Data Pipeline

Tools: Python, Pandas, Matplotlib, Statsmodels, Alpha Vantage API

? Built an end-to-end financial data pipeline for real-time stock data ingestion, preprocessing, and transformation.

? Developed ARIMA-based time-series forecasting models to predict stock price trends and market behavior.

? Performed exploratory data analysis (EDA) on financial datasets to identify trends, volatility, and correlations.

? Integrated Alpha Vantage API for automated real-time financial data retrieval.

? Designed an interactive Streamlit dashboard for stock visualization, forecasting insights, and decision support.

? Structured and processed financial datasets for scalable analytics and machine learning workflows.

NLP-Based Resume Analysis & Semantic Matching System

Tools: Python, NLP, Streamlit

? Built an NLP-based system to extract and analyze structured information from unstructured resume data.

? Implemented semantic matching techniques to evaluate resume relevance against job descriptions.

? Designed scoring algorithms based on skill extraction and contextual similarity.

? Explored embeddings-based approaches for improving semantic search and ranking.

Intelligent Financial Document Insights System (RAG + LLM)

Tools: Python, FAISS, HuggingFace Transformers, Sentence-Transformers, Streamlit, Pandas

? Built an AI-powered system to process and analyze financial documents using NLP and machine learning techniques.

? Designed a data pipeline to extract, clean, and structure unstructured PDF-based financial data.

? Implemented a Retrieval-Augmented Generation (RAG) pipeline using FAISS for semantic search and efficient document retrieval.

? Generated vector embeddings using transformer models such as all-MiniLM-L6-v2 for context-aware querying.

? Integrated a Large Language Model (DistilGPT2) to generate natural language responses from financial documents.

? Performed exploratory data analysis (EDA) to identify key financial trends and document patterns.

? Developed an interactive Streamlit dashboard for real-time querying and financial insights visualization.

Skills

Programming Languages: Python, SQL

Tools: Tableau, Power BI, Advanced Excel

Frameworks: TensorFlow, PyTorch (basic), Flask, Streamlit

Libraries: Pandas, NumPy, Scikit-learn, PySpark, Matplotlib, Seaborn, OpenCV,

Concepts & Techniques: Machine Learning, Deep Learning, NLP, ETL, Data Visualization, Time-Series Analysis, RAG.

Education

Bunts Sangha?s S.M. Shetty College Powai,Mumbai

Bachelor of Data Science CGPA: 8.60 / 10

2022 - 2025

CERTIFICATION

Analyzing Data With Power BI

Contact this candidate