Muhammad Owais

I'm a recent graduate in Artificial Intelligence with a strong foundation in machine learning, deep learning, and data science. I'm eager to leverage my skills and knowledge to solve real-world problems and make a meaningful impact.

Respectful self-motivator gifted at finding reliable solutions for software issues. Experienced in data analysis and model development and offering skills in Python and TensorFlow. Fluent in English and accustomed to working with cross-cultural, global teams.

Hardworking and passionate job seeker with strong organizational skills eager to secure an entry-level Data Scientist position. Ready to help the team achieve company goals.

Customer Churn Prediction: Developed a predictive model to identify customer churn using the "Telco Customer Churn" dataset from Kaggle. The project involved data cleaning, handling missing values, and encoding categorical variables. I engineered features and selected the most relevant ones using RFE and ensemble model importance. Various models were tested, with LightGBM achieving the best results (precision: 65%, recall: 55%, AUC: 0.85). The final model was deployed in a Streamlit app for interactive churn predictions.

• Technologies used: Python, Pandas, Scikit-learn, LightGBM, SHAP, and Streamlit.

Deep Learning for Medical Image Processing (MIP): Developed advanced deep learning models to analyze and interpret medical images for early detection and diagnosis. The project involved designing and implementing Convolutional Neural Networks (CNNs) to classify and segment medical images, with a focus on enhancing diagnostic accuracy. Conducted a comprehensive review of deep learning techniques in medical imaging and contributed to optimizing algorithms for improved performance in clinical settings.

• Technologies Used: Python, TensorFlow, Keras, OpenCV.

Malaria Detection Using Faster R-CNN: Developed a machine learning model to detect malaria from blood smear images using Faster R-CNN. The project included data preprocessing, exploratory data analysis (EDA), model training, and prediction. Implemented Faster R-CNN for accurate detection and classification of malaria-infected cells, enhancing diagnostic accuracy.

• Technologies Used: Python, TensorFlow, Keras, Pandas, NumPy, Matplotlib, OpenCV

Natural Language Processing (NLP): Engaged in multiple NLP projects focusing on text preprocessing, vectorization, sentiment analysis, and text classification. Developed and implemented various models and techniques using Python to process and analyze large datasets of text. Conducted experiments with different algorithms for tasks such as named entity recognition (NER) and text normalization, enhancing the understanding and application of NLP in real-world scenarios.

• Technologies Used: Python, NLTK, SpaCy, Scikit-learn, TensorFlow, Pandas, NumPy.

Internship Project:

• Developed a Python-based automated system to download and organize email attachments from Microsoft Outlook. The system retrieves emails, downloads attachments, and sorts them into folders based on file types.
• Implemented logging for attachment tracking and integrated the solution to run as a background process with system tray notifications.

Technologies Used: Python, pandas, win32com.client, openpyxl

all above mentioned projects are available on given GitHub Repository. (https://github.com/MuhammadOwais02)

Machine Learning Specialization - Coursera KJPRKQDM9LDP

+923202057469

owais.sajid002@gmail.com