Data Scientist - Python, ML/DL, Predictive Analytics
Resume:
Shruti Gupta
Jr Data Scientist
+91-742******* ***************@*****.*** Nagpur, INDIA Experience: 2 Years 0 Month www.linkedin.com/in/shruti-gupta-a66344280
Profile summary
Junior Data Scientist with experience in data analysis, machine learning, and model development. Skilled in Python, SQL, and TensorFlow, with expertise in data preprocessing, EDA, and building predictive models. Proficient in visualizing insights using Power BI and Tableau to support data-driven decision-making. Strong problem-solving abilities with a keen eye for detail and a passion for optimizing model performance. Collaborative team player with a solid foundation in statistical analysis and data interpretation, eager to contribute to impactful projects and grow in the field of data science. Skills
Computer Vision Deep Learning Data Mining Excel Tableau Power BI Logistic Regression MySQL Text Mining Regression Statistics Natural Language Processing Python Data Analytics Data Science Machine Learning Artificial Intelligence Advanced Excel Work Experience
Jr Data Scientist – Codebook
As a Junior Data Scientist, I am responsible for analyzing and interpreting structured and unstructured data to support data- driven business decisions. My role involves data collection, data cleaning, and preprocessing, followed by conducting Exploratory Data Analysis (EDA) to identify patterns, trends, and actionable insights. I collaborate closely with senior data scientists to design, build, train, and evaluate machine learning models using Python, Scikit-learn, TensorFlow, and related libraries. I contribute to feature engineering, model optimization, and performance evaluation to improve model accuracy and reliability. Additionally, I create clear and impactful data visualizations using Power BI, Tableau, Matplotlib, and Seaborn to communicate insights to both technical and non-technical stakeholders. With a strong foundation in Pandas and NumPy, I support data- driven strategies by translating analytical findings into practical recommendations. My analytical mindset, problem-solving skills, and attention to detail help deliver meaningful insights and improve overall model performance. Data Scientist – ExcelR
As a Freelance Data Scientist, I delivered end-to-end data science and machine learning solutions for multiple clients across different domains. My responsibilities included understanding business requirements, collecting and preprocessing data, performing Exploratory Data Analysis (EDA), and building predictive and analytical models using Python, Pandas, NumPy, and Scikit-learn.
I developed and deployed machine learning models for classification, regression, and NLP-based use cases, ensuring model performance through proper validation and evaluation techniques. I also worked on Generative AI and NLP solutions, including LLM-based chat automation, document question-answering systems, and text summarization using LangChain and embedding-based retrieval.
Additionally, I built scalable data pipelines for structured and unstructured datasets and created meaningful data visualizations using Power BI, Tableau, and Matplotlib to present insights to clients. Through continuous client interaction and iterative improvements, I delivered data-driven solutions that improved decision-making efficiency and automation. Projects
Multimodal Conversational Chatbot (MCP-based)
• Developed a simple conversational chatbot using a Multimodal Conversational Pipeline (MCP) that integrates text and image 1 Weeks
2023
2020
2018
inputs for enhanced user interaction.
• Used pretrained transformer models (e.g., BERT, Vision Transformer) to handle multimodal input processing and response generation.
• Implemented a basic retrieval-augmented pipeline that allows the chatbot to search a small document base and generate contextual responses.
• Added support for image captioning to interpret uploaded images and respond accordingly using natural language generation techniques.
• Gained hands-on experience with Gen-AI workflows, prompt engineering, and the early implementation of Retrieval- Augmented Generation (RAG) concepts.
DocuBot: AI Chatbot for Visual and Textual Document Query
• Developed DocuBot, an AI-powered multimodal chatbot capable of understanding and answering queries based on both textual and visual documents (e.g., PDFs, scanned images, screenshots).
• Integrated Optical Character Recognition (OCR) using Tesseract and PaddleOCR to extract meaningful text from uploaded visual documents.
• Utilized sentence embedding techniques (e.g., SBERT) to match user queries with document segments for accurate context retrieval.
• Incorporated a Multimodal Conversational Pipeline (MCP) by fusing visual input and user prompts to create context-rich query vectors for response generation.
Focused on Gen-AI safety and transparency, including summarization features and source highlighting to help users understand the basis of each answer.
• Explored use cases in legal document QA, research paper assistance, and invoice/exam paper analysis, making DocuBot a scalable tool for intelligent document interaction. Education
BCA Computers
G.H Raisoni College of Commerce and Science Technology Grade - 8.2/10
12th
Maharashtra, English
Marks - 88.0%
10th
Maharashtra, English
Marks - 80-84.9%
Additional information
Languages: English, Hindi
Contact this candidate