Machine Learning
Customer Churn Prediction
A supervised-learning study comparing classification approaches for identifying customers who may leave a service.
Case study · Machine Learning
MediSight AI
ML engineering · Internship
An explainable healthcare risk-modelling workflow built around model evaluation, experiment tracking, and a clinician-facing interface.
01 / Context
The problem
Healthcare prediction work is not only about producing a score. Models need reproducible experiments, understandable feature contributions, and clear boundaries around what a prediction can and cannot say.
My role: Machine Learning Intern at Ezitech Institute (Eziline Software House); contribution described in the project repository and CV.
02 / Implementation
How it works
01Prepare and compare
The workflow organizes dataset-specific preprocessing and classifier benchmarking, rather than treating different clinical prediction tasks as one interchangeable problem.
02Track experiments
MLflow provides a record of model runs so evaluation can be compared and revisited instead of relying on notebook state.
03Expose explanations
SHAP is used to inspect feature contributions. Explanations describe model behaviour; they are not clinical reasoning or proof of causality.
04Serve the workflow
A FastAPI service connects model operations to a Next.js interface, with Supabase used for application data and supporting functionality.
Implementation highlights
- Model training and benchmarking across seven de-identified healthcare dataset domains
- SHAP-based explanation workflow exposed through a FastAPI service
- Experiment tracking with MLflow and an interface for reviewing model behaviour
- MLOps-oriented drift monitoring and retraining workflow documented in the project
03 / Evidence
What can be verified
The points below summarize the public repository and owner-provided CV where noted. Read the source for implementation details and the evaluation setup before drawing further conclusions.
Evaluation0.8307 AUC–ROC
LightGBM result stated in the CV/project notes; task-specific context should be checked before comparing with other models.
Datasets7 domains
De-identified healthcare dataset domains described in project documentation.
ReproducibilityMLflow
Experiment tracking is part of the documented stack.
04 / Boundaries
Limitations and next questions
- Results depend on the dataset, target definition, split strategy, and class balance; a single score should not be generalized across clinical use cases.
- The system is a technical project, not a certified medical device or a substitute for professional judgement.
- Dataset-level details and evaluation protocols should be reviewed in the repository before using results for research conclusions.
Evidence-first note: a live demo demonstrates an interface and workflow; it does not by itself validate model quality, security, or real-world impact.
Continue exploring