Muhammad Haseeb
AI-specialist automating workflows and systems
- 1
- Followers
End-to-End Customer Churn Prediction ML Pipeline
Built a reusable end-to-end machine learning pipeline for predicting customer churn using the Telco Customer Churn dataset and Scikit-learn's Pipeline API.
The project combines data preprocessing, feature engineering, model training, hyperparameter optimization, and evaluation into a single reproducible workflow. I implemented separate preprocessing for numerical and categorical features using StandardScaler and OneHotEncoder, then integrated the preprocessing with Logistic Regression and Random Forest models.
Key work:
Built reusable Scikit-learn pipelines using Pipeline and ColumnTransformer
Implemented numerical scaling and categorical feature encoding
Trained and compared Logistic Regression and Random Forest models
Performed hyperparameter optimization using GridSearchCV and StratifiedKFold
Evaluated models on held-out test data
Serialized the complete trained pipeline using Joblib for reuse in applications
Selected the best-performing model based on test performance
1
225
IMDB Movie Review Sentiment Analysis
Built an end-to-end Natural Language Processing system to classify 50,000 IMDB movie reviews as positive or negative.
The project includes a complete text preprocessing pipeline with tokenization, stop-word handling, POS-aware lemmatization, and negation preservation. I used TF-IDF vectorization with unigram and bigram features and trained and compared four machine learning models: Logistic Regression, SVM, Naive Bayes, and KNN.
The best-performing models achieved approximately 90% accuracy, with SVM and Logistic Regression producing the strongest results. I also built a Streamlit web application that allows users to enter reviews, select a trained model, and receive real-time sentiment predictions with confidence scores.
Key work:
Developed an end-to-end NLP preprocessing pipeline
Implemented TF-IDF feature extraction with n-grams
Trained and compared four classification algorithms
Evaluated models using accuracy, precision, recall, confusion matrices, and classification reports
Serialized trained models for deployment
Built a real-time Streamlit inference application
1
186
Filmey — AI-Powered Director Assistant
Built an AI-powered film direction assistant that transforms creative ideas into structured cinematic concepts and production guidance.
The application uses AI to help users develop scenes by generating scene descriptions, shot ideas, camera direction, lighting, environments, and visual concepts, making the creative planning process faster and more structured.
Key work:
Designed an AI workflow for turning natural-language ideas into cinematic scene plans
Integrated AI APIs for intelligent content generation
Generated detailed shot, lighting, environment, and visual direction suggestions
Built an interactive application around the AI workflow
Focused on combining NLP and generative AI with a practical creative use case
1
137
Contlify — AI-Powered Brand Intelligence
0
0