Skip to content
View SercanTeyhani's full-sized avatar
  • Turkey

Block or report SercanTeyhani

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
SercanTeyhani/README.md

👋 Hello! I’m Sercan Teyhani – Passionate about Data Science, Machine Learning, and Generative AI

I'm an aspiring Data Scientist passionate about Machine Learning, Natural Language Processing, SQL, Python, Generative AI, and Data Analysis. I focus on extracting meaningful insights from complex data and transforming those insights into innovative, real-world applications that leverage the power of generative AI to create intelligent and adaptive solutions.

This GitHub profile showcases my skills and problem-solving approach through various projects. I am especially interested in pursuing a career in Data Science and Machine Learning in Germany. Additionally, I am curious about cloud technologies and eager to learn more in this area. I believe the skills I demonstrate here will add valuable contributions to Germany’s tech ecosystem.

📫 Contact:

🚀 Featured Projects

  1. 📺 YouBot — YouTube Comment Analysis & Chatbot
    A Streamlit-powered web application designed to help users analyze YouTube video comments using cutting-edge Natural Language Processing (NLP) techniques, including BERTopic and sentiment analysis (VADER & TextBlob). In addition to exploratory data insights, YouBot features a conversational assistant powered by Google's Gemini 1.5 Flash model, integrated with a Retrieval-Augmented Generation (RAG) pipeline. Technologies: Streamlit, Python, Pandas, Requests, TextBlob, VADER, SpaCy, NLTK, Gensim (LDA), BERTopic, Matplotlib, Seaborn, Plotly, LangChain, Google Gemini API, YouTube Data API v3
    Highlights: Dual sentiment analysis, topic modeling (LDA & BERTopic), comment trend analysis, RAG-based AI chatbotLive
    Live Demo: https://youbot.streamlit.app/
    Medium Article: https://medium.com/@sercanteyhani/youbot-understanding-youtube-comments-and-chatting-intelligently-an-engineers-perspective-71fc82164a26

  2. 🩺 Obesity Prediction Project
    A comprehensive machine learning project that predicts obesity levels based on individuals’ health metrics and lifestyle behaviors. Includes data preprocessing, feature engineering, model building, evaluation, and deployment with a Streamlit web app.
    Technologies: Python, Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn, Joblib, Streamlit
    Highlights: Label Encoding, StandardScaler, Logistic Regression (Newton-CG), Class Weighting, BMI creation, SHAP feature importance analysis
    Live Demo: https://obesity-test.streamlit.app/
    Medium Article: https://medium.com/@sercanteyhani/predicting-obesity-with-machine-learning-from-raw-data-to-real-time-web-app-5e601f4267e5

  3. 🧠 Career Path Recommendation System with NLP & Gemini API & LinkedIn
    An intelligent recommendation system suggesting career paths in Data Science by analyzing user’s past experiences and aligning them with real job market trends. Utilizes LinkedIn job postings and Google Gemini API.
    Technologies: Selenium, BeautifulSoup, BERTopic, spaCy, N-grams, Gemini API (Google’s LLM), WordCloud, c-TF-IDF, Streamlit
    Highlights: LinkedIn data scraping, topic modeling, large language model reasoning, personalized career path suggestions
    Live Demo: https://data-mentor.streamlit.app/
    Medium Article: https://medium.com/@sercanteyhani/from-linkedin-profiles-to-career-paths-an-llm-powered-recommendation-system-e2e2d9f22ed5

  4. 📊 MTA Metro Ridership Analysis & Exploratory Data Analysis (EDA)
    A detailed exploratory data analysis of New York City MTA metro ridership data focusing on December 2023. Aims to reveal passenger patterns by stations, hours, and boroughs.
    Technologies: Python, Pandas, Matplotlib, Seaborn
    Highlights: Time-based analysis, station-level insights, borough comparisons, actionable insights for workforce allocation optimization
    Medium Article: https://medium.com/@sercanteyhani/from-subways-to-support-using-mta-data-to-drive-cancer-awareness-eda-project-4057fa048de6

🇩🇪 Career Goal in Germany
With my passion for machine learning and data science and practical experience in the field, I am seeking a position at innovative tech companies in Germany. I am especially excited to join teams developing AI and data-driven solutions. I believe Germany’s leadership in technology and engineering aligns perfectly with my career ambitions.

I am open to discussions regarding open positions or potential collaborations.

🎉 Stay Connected!
If you have any questions about my projects or just want to chat, feel free to reach out. Follow my GitHub activity to stay updated on my latest work.

Popular repositories Loading

  1. youtube-comment-analyzer-chatbot youtube-comment-analyzer-chatbot Public

    A Streamlit application for YouTube comment sentiment analysis, topic modeling (LDA & BERTopic), historical comment trends, and an interactive chatbot using LangChain and Google Generative AI.

    Jupyter Notebook 3

  2. obesity-test obesity-test Public

    A machine learning pipeline to classify obesity levels from structured health and habit data using Python, scikit-learn, and Streamlit.

    Jupyter Notebook 1

  3. nlp-recommendation-system nlp-recommendation-system Public

    Intelligent system that matches user experience with real Data Science job market trends using NLP & LLMs.

    Jupyter Notebook 1

  4. EDA-subway-cancer-awareness EDA-subway-cancer-awareness Public

    Exploratory data analysis of NYC subway data to identify high-traffic stations for cancer awareness donation campaigns.

    Jupyter Notebook 1

  5. SercanTeyhani SercanTeyhani Public

    1