mubashir-yaseen Goto Github PK

👋 Hello! I'm Mubashir, a data scientist passionate about deriving insights from data and solving real-world problems.

• 🎓 Graduated in Electrical Engineering from National University of Sciences and Technology (NUST).
• 💼 Currently exploring the intersection of data science and Electrical Engineering.
• 🌱 Keen on continuous learning and staying updated with the latest in data science.

• Programming Languages: Python, R
• Data Analysis: Pandas, NumPy
• Machine Learning: Scikit-learn, TensorFlow
• Deep Learning Frameworks: TensorFlow, Keras, PyTorch
• Natural Language Processing (NLP): NLTK
• Database: SQL
• Cloud Platforms: AWS, Azure, Google Cloud Platform (GCP)
• Version Control: Git, GitHub
• Visualization: Matplotlib, Seaborn
• Statistical Analysis: SciPy, StatsModels
• Data Cleaning and Preprocessing: scikit-learn's preprocessing module, pandas
• Experimentation and A/B Testing: Designing experiments, analyzing results
• Time Series Analysis: Prophet, ARIMA models
• Feature Engineering: Creating new features from existing data to improve model performance
• Model Deployment: Docker, Flask, Streamlit
• Data Engineering: ETL (Extract, Transform, Load) processes, data pipelines
• Quantitative Analysis: Statistical modeling, hypothesis testing
• Collaboration and Communication: Effective communication skills, teamwork, presentation skills

Developed a movie recommendation system using collaborative filtering techniques, analyzing user-item interactions to generate personalized recommendations for users. The system incorporates user feedback to automatically update and refine recommendations which makes it really smart.

• Utilized collaborative filtering based on user-item interactions.
• Implemented recommendation generation for users.
• Integrated evaluation metrics to assess recommendation quality.
• Incorporated user feedback for refining recommendations, automatically updating recommendations based on user interactions.

• Python: Core language for development.
• Flask: Web framework for creating the web application.
• TMDB API: Used for fetching movie data.
• Pandas and NumPy: Data manipulation and analysis.
• Scikit-learn: Machine learning algorithms for collaborative filtering.
• HTML/CSS: Frontend design of the web application.

Live Demo

mubashir-yaseen/recommendation_sys

• Implemented Analyzing of Historical Stock/Revenue Data and Building a Dashboard
• Key Features: Data wrangling and preprocessing, Exploratory data analysis (EDA), Model development using machine learning algorithms, Evaluation of model performance and refinement
• Technologies used: Webscraping using yfinance library and BeautifulSoup.
• https://github.com/mubashir-yaseen/DataScience_Assignments/blob/197393c23a6e6ab87b2a3c6d6bcce5c408fd1138/Extracting%20and%20Visualizing%20Stock%20Data.ipynb

• Analyzed historical house sales data in King County, USA, & Build predictive models for house prices.
• Key Features: Data wrangling and preprocessing, Exploratory data analysis (EDA), Model development using machine learning algorithms, Evaluation of model performance and refinement
• Technologies Used: Python, pandas, matplotlib, NumPy, seaborn, scikit-learn
• https://github.com/mubashir-yaseen/DataScience_Assignments/blob/8439475fedb89165c9d24922db1062adda4fcfe7/House_Sales_in_King_Count_USA-20231003-1696291200.jupyterlite.ipynb
• Conclusion: The project showcased proficiency in data analysis, machine learning, and model evaluation techniques, providing valuable insights into house price predictions in King County, USA. Future enhancements may include feature engineering, model tuning, and deployment of predictive models.

• LinkedIn: https://www.linkedin.com/in/muhammad-mubashir-38a1361a1/
• GitHub: https://github.com/mubashir-yaseen
• Email: [email protected]

-->