Inam Ali
Data Scientist turning messy data into ML-driven insights
New to Contra
Inam is ready for their next project!
Mental Health Treatment Prediction is a Python-based classification project that analyzes mental health survey data to predict whether an individual is likely to seek treatment. The pipeline covers the full workflow data cleaning, label encoding of categorical features, feature engineering, model training, and evaluation culminating in a visualization output that summarizes key patterns in the data. It's a practical example of applying classification models to a sensitive, real-world behavioral health question.
0
4
Retail Sales Analysis with Customer Segmentation is a Python project that combines sales data cleaning with K-Means clustering to uncover distinct customer groups. The pipeline automatically cleans raw retail data (handling duplicates, missing values, and date formatting), aggregates transactions to the customer level, and applies RFM analysis (Recency, Frequency, Monetary) to quantify purchasing behavior. From there, K-Means clustering groups customers into segments based on behavior, demographics, and engagement patterns turning messy raw sales data into targeted business strategies for each customer group.
0
10
A customer segmentation analysis tool built with Python that uses K-Means clustering to group customers by purchasing behavior. The project covers a full ML pipeline from data loading and preprocessing to feature normalization, optimal cluster selection, and visualization turning raw transaction data into actionable business insights for targeted marketing and customer strategy.
1
28
MediFind Pakistan is a full-stack AI healthcare app that helps users identify likely conditions from their symptoms. A Random Forest model trained across 41 diseases and 131 symptoms powers the prediction engine, paired with a Gemini-powered chatbot that responds fluently in both English and Urdu making health guidance accessible to a wider audience. Built end-to-end with a FastAPI backend, it's designed as a practical example of applying ML to a real-world problem in an underserved market.
0
31