This repository contains a collection of AI/ML projects completed as part of the Great Learning AIML program and General Assembly. Each project focuses on a specific domain or technique—ranging from EDA and predictive modeling to computer vision and NLP—implemented using Python and industry-standard libraries.

Each project folder includes:

• code/: notebooks and scripts
• data/: input data and derived features
• images/: plots, visuals, and diagrams
• Presentation.pdf: project summary slides
• README.md: project-specific documentation

Performed EDA using NumPy, Pandas, and Seaborn to uncover demand patterns in cuisines and restaurants, and provided business recommendations.

Analyzed customer attributes and built a decision tree model to predict loan acquisition likelihood and guide marketing strategies.

Built a predictive model to classify churn behavior using Random Forest, Bagging, Boosting, SMOTE, and hyperparameter tuning.

Developed an artificial neural network from scratch to identify high-risk churn customers using TensorFlow and Keras.

Built an image classifier to distinguish plant seedlings and weeds using TensorFlow, image processing, and transfer learning.

Built an AI-driven system to extract and summarize market sentiment from news articles using LLMs, Transformers, Prompt Engineering, and text preprocessing.

Comprehensive geospatial analysis of SAT/ACT requirements vs. state averages

Common helper functions and scripts are located in the utils/ folder.

• Python, Jupyter
• Pandas, NumPy, Scikit-learn
• TensorFlow, Keras
• Matplotlib, Seaborn
• Gensim, Transformers, llama-cpp

• All projects were developed independently by Azin Faghihi.
• Content is based on project work from the Great Learning AIML curriculum.
• Data has been anonymized or sourced from course datasets.