Hi there! I'm Muneeza, a Data Scientist with a strong interest in machine learning and deep learning. I have skills in Python, SQL, machine learning and deep learning algorithms, and Power BI, and I'm actively working on projects related to machine learning and data analysis.
Through hands-on projects and self-directed learning, I'm exploring the intricacies of data science and machine learning, seeking to understand how data-driven insights and predictive models can drive meaningful change in various domains. From manipulating datasets and extracting valuable information to crafting compelling visualizations and building machine learning models, I'm constantly pushing myself to learn and grow in this dynamic field.
Projects completed
GitHubPassionate Data Scientist with a strong inclination towards data analysis and visualization. Proficient in Python, SQL, Excel, and Power BI, adept at transforming complex data into actionable insights and visually compelling dashboards.
Check out my CV for detailed experience and projects:
Download CVStudied data mining techniques including classification, clustering, association, and anomaly detection, with a focus on extracting valuable insights from large datasets.
Learned key statistical techniques like probability, hypothesis testing, and regression analysis, applied to data science problems for insightful decision-making.
Demonstrates proficiency in Python, covering syntax, data structures, and libraries like NumPy, Pandas, Matplotlib, and Seaborn.
Gained deep insights and practical skills in various machine learning techniques and algorithms to solve real-world problems.
Completed a course on image recognition using Machine Learning, gaining expertise in applying Machine Learning models for object classification and image analysis.
Mastered tools and algorithms to enable machines to ‘see’ and understand the world, with practical skills in object detection and AI-driven visual analysis.
CGPA: 3.96
Grade: A+
Below are the sample Data Analytics projects on SQL, Python, Power BI & ML.
This project focuses on using genomic selection techniques to predict key traits in wheat, such as yield and plant height, using genotype and phenotype data. We implemented various machine learning models including Random Forest, XGBoost to select the most important SNPs (genetic markers) for accurate trait prediction.
Tools used include Python, Pandas, Scikit-learn, Matplotlib, Pyplot, Seaborn, Beagle, Plink. The model pipeline includes data cleaning, feature selection using GWAS and ML, imputation using Beagle, and performance comparison across models.
A content-based recommendation system. The project features an interactive Streamlit interface, visualizations, and a machine learning engine for personalized job recommendations.
This system matches job seekers to suitable roles based on job descriptions, helping users find relevant positions efficiently. The model utilizes text processing techniques like TF-IDF and uses cosine similarity to recommend similar roles.
I developed a web app using Streamlit that predicts resume categories based on their content, aimed at helping recruiters automate resume classification, and Plotly.
I developed an interactive UI for instant resume category predictions using NLP techniques like tokenization and lemmatization. I trained a KNN classifier with TF-IDF vectorization and deployed the model in a Streamlit app. This project showcases my skills in NLP, machine learning, and interactive web applications using Python and relevant libraries.
I analyzed customer data from a PostgreSQL database to uncover insights and predict revenue based on demographics.
Key highlights include: Visualizing revenue by expense type with Plotly Treemap Identifying top states by total revenue, average annual fees by age group. Predicting revenue using a Random Forest Regressor model.
Tool used: Excel
Key Visualizations: Sales trends by category, month, channel, and gender, providing insights into customer demographics, sales patterns, and regional performance for data-driven decision-making. This analysis highlighted key trends, optimizing marketing and inventory strategies.
Tools Used: Power BI
Project Overview: Analyzed and visualized supermarket sales data with key features including cards displaying the sum of quantity, sales, and shipped orders. Implemented year slicers for dynamic filtering. Key visualizations included sales distribution across different markets and detailed profit analysis by product categories and sub-categories.
Tools Used: PostgreSQL, Power BI
Project Overview: Dashboard for analyzing credit card sales data with key features such as data integration from PostgreSQL to Power BI, and revenue calculations consistent with Python results. Visualizations include revenue trends over time, key sales metrics like total sales, average transaction value, and customer segmentation, along with dynamic filters for deeper insights and analysis.
Below are the details to reach out to me!
Punjab, Pakistan