Churn Risk Scoring API for Telecom Subscriber Retention

Added Jun 2025 3 design docs

Marketing and retention systems at telecom companies increasingly need churn intelligence delivered as a service: a CRM or campaign tool calls an API with a subscriber profile and gets back a risk score in milliseconds. This project focuses on building exactly that production-style inference backend, rather than a notebook that never leaves the data science team. The intern trains an XGBoost churn model in Python and wraps it in a FastAPI service with dedicated endpoints for single and batch predictions plus a model explanation endpoint powered by SHAP, so consuming systems can retrieve both a score and its top contributing factors. Request and response schemas are validated with typed models, and the automatically generated Swagger UI makes every endpoint testable from the browser. The service is containerized with Docker and deployed to Hugging Face Spaces, giving the intern a live, shareable URL for their working API. The project teaches the machine learning engineering side of data science: serializing and versioning models, designing inference APIs, documenting them for other developers, and shipping a containerized service to a public host — the skills that separate deployable work from experiments.

Related projects

Explainable Churn Prediction Workbench for Telecom Retention Teams

Telecom operators lose a meaningful share of subscribers every quarter, and retention teams cannot act on a churn score alone — they need to know why a specific customer is flagged so they can choose the right offer or intervention. This project builds a full-stack application that pairs accurate churn prediction with human-readable explanations. The intern explores and prepares subscriber data with pandas and NumPy in Jupyter, trains an XGBoost classifier with scikit-learn tooling for validation, and applies SHAP to attribute each prediction to concrete drivers such as contract type, tenure, or support call history. A FastAPI backend serves the model behind clean prediction and explanation endpoints, while a Streamlit interface lets analysts upload customer records, review churn probabilities, and inspect force plots and feature importance charts interactively. The application is containerized with Docker so the full stack can be deployed as a single unit. By finishing the project the intern demonstrates the complete applied machine learning workflow — data preparation, model training, interpretability, API design, and deployment — and shows they can turn a black-box model into a decision-support tool a business team would actually use.

telecommunicationsdata-sciencedocker+10

View project

Hard

Telecom Network Anomaly Detection and Outage Prediction Suite

Telecom operators run networks where minutes of downtime translate into thousands of frustrated customers and costly SLA penalties, yet operations centers still spend much of their time reacting to outages after users report them. The competitive edge lies in detecting anomalies early and predicting failures before they cascade across the network. The intern develops a network analytics suite where agentic AI monitors performance continuously. A Flask backend in Python ingests real-time network telemetry, including latency, packet loss, and per-node throughput, into MongoDB, and AI agents analyze the streams to detect anomalies, correlate symptoms across the topology, and predict likely outages together with recommended interventions. Interactive dashboards give network operators live views and drill-downs, automated alerting pushes prioritized incidents to the right teams, and Docker containerizes the services for scalable deployment. Secure user management controls who can see and act on each network segment. The intern practices building AI-driven operations tooling: streaming telemetry design, agent workflows that explain their findings, and the alerting discipline that separates useful monitoring from noise.

telecommunicationsagentic-aidocker+3

View project

Medium

Symptom-Based Early UTI Screening Tool for Rural Healthcare

Urinary tract infections are among the most common infections affecting women worldwide, yet in rural and underserved communities they often go unnoticed until they escalate into painful, costly complications. Seeing a clinician for an early assessment is not always practical, so a lightweight screening tool that works from symptom descriptions and basic health data can make a real difference in prompting timely care. The intern builds a complete screening application around this need. A questionnaire-style interface built with streamlit collects symptoms such as burning sensation, urinary frequency, and fever alongside simple health indicators, and a machine-learning classifier written in python estimates the likelihood of a UTI from those inputs. A fastapi backend exposes the trained model as an inference service, validates incoming data, and keeps the interface cleanly separated from the prediction logic. The app also surfaces educational content on symptoms, prevention, and red flags that warrant an urgent doctor visit. Completing the project takes the intern through the full arc of applied machine learning in healthcare: preparing training data, evaluating a classifier honestly, serving it behind an API, and presenting predictions responsibly as guidance rather than diagnosis.

healthcarefastapimachine-learning+2

View project