8000 Afnan107 · GitHub
[go: up one dir, main page]

Skip to content
View Afnan107's full-sized avatar

Block or report Afnan107

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

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

Report abuse
Afnan107/README.md

Data Scientist

Technical Skills: Python, SQL, Machine Learning, Deep learning, NLP, AI

Education

  • Bachalors in Computer Application | Vishwakarma Institute of Technology (May 2021)

Projects

Digital Marketing Campaign Analysis and App Development

Publication

  • Analyzed digital marketing campaigns using Python, employing advanced data preprocessing, and visualization techniques.
  • Executed a data-driven analysis of digital marketing campaigns using Python, applying advanced techniques like SMOTE for handling imbalanced data.
  • Developed and deployed a machine learning model to predict campaign success, enhancing targeting accuracy.
  • Created a Python-based app for streamlined campaign data management and automated reporting.
  • Designed a Power BI dashboard providing real-time insights and facilitating strategic decision-making.
  • Delivered actionable insights that optimized campaign performance, improved ROI, and supported data-driven marketing strategies.

Impact:

  • Improved campaign management efficiency by automating data handling processes.
  • Enhanced decision-making capabilities through real-time and interactive dashboards

EEG Band Discovery

Forecasting of Supermarket Sales using SARIMA model

Publication

  • Checked for seasonality and stationarity of data
  • Executed a data-driven sales forecasting project for a supermarket chain, employing SARIMA, Prophet, and XGBoost models to predict weekly sales.
  • Optimized the SARIMA model to achieve the lowest MAPE of 35%, indicating high predictive accuracy for a 90-day sales dataset.
  • Leveraged Prophet and XGBoost for comparative analysis, obtaining MAPEs of 47% and 41%, respectively, demonstrating versatility in model application.
  • Enabled strategic inventory and staffing decisions through actionable sales insights, contributing to operational efficiency and reduced wastage.
  • Positioned the business to better meet customer demand and enhance profitability through informed data-centric forecasting methodologies."

Bike Study

Popular repositories Loading

  1. Afnan107 Afnan107 Public

    Jupyter Notebook

  2. example-portfolio example-portfolio Public

    Forked from ShawhinT/example-portfolio

    Example data science portfolio

  3. leap-day leap-day Public

    Forked from pages-themes/leap-day

    Leap day is a Jekyll theme for GitHub Pages

    SCSS

  4. minimal minimal Public

    Forked from pages-themes/minimal

    Minimal is a Jekyll theme for GitHub Pages

    SCSS

0