Machine Learning Travel Destination Risk Assessment Tool

Added Jun 2025 3 design docs

Travelers routinely book trips without a clear picture of conditions at their destination, from weather disruption to health advisories to local safety trends, because that information is scattered across dozens of sources. A single tool that scores destination risk from recent data helps people plan smarter itineraries and pack the right contingencies. The intern builds a Flask web application in Python where a user enters a destination and travel dates and receives a predicted risk profile. Under the hood, the intern assembles historical and recent data covering advisories, incident rates, and weather patterns into a training set, engineers features from it, and fits a machine learning classifier that outputs risk levels together with the factors that drove them. The app presents results as a clear, non-alarmist summary with practical suggestions, and the data science pipeline is kept reproducible so the model can be retrained as fresh data arrives. Completing the project teaches supervised classification on messy real-world data, honest communication of model uncertainty to everyday users, and the craft of packaging predictions into a web experience people can actually act on before a trip.

Related projects

Traffic Camera Vehicle Detection and Counting Dashboard

Cities and transportation departments make road investment and signal timing decisions with surprisingly little data, because manual traffic counts are expensive and in-road sensors are costly to install and maintain. Existing traffic cameras already watch most busy intersections, making software the cheapest path to reliable vehicle counts. The intern builds a Streamlit dashboard that analyzes traffic footage using two generations of computer vision: a classical detector combining HOG features with an SVM classifier, and a modern YOLO deep learning model running on PyTorch. The application processes video with OpenCV, draws detections onto the footage, counts vehicles crossing defined zones, and aggregates results with NumPy into traffic analytics such as per-interval volumes and detection confidence summaries. A comparison view puts the classical and neural pipelines side by side so users can evaluate accuracy against processing cost on the same clip. Through the build, the intern learns how detection models are evaluated in a practical setting rather than on benchmark leaderboards, develops skills in video processing and counting logic such as line-crossing checks, and demonstrates the ability to deliver a decision-support dashboard for a real civic use case.

transportationcomputer-visionnumpy+4

View project

Hard

Fleet Emissions Monitoring and Reporting Platform for Transport Operators

Transportation companies face mounting pressure from regulators, customers, and their own fuel budgets to cut fleet emissions, yet most operators cannot say with confidence how much CO2 each vehicle, route, or driver produces. Without that visibility, sustainability targets stay aspirational and compliance reporting becomes a quarterly scramble. The intern builds a platform that makes emissions measurable and actionable. A Python service ingests real-time vehicle telemetry covering fuel burn, mileage, and idling, then computes per-vehicle and per-route emissions, while predictive analytics forecast fleet totals and flag high-impact outliers worth immediate attention. A Node.js API serves the data to a Next.js dashboard where operations managers track trends, drill into individual vehicles, and generate regulator-ready compliance reports. MongoDB stores telemetry and fleet records, and Docker packages every service so the platform deploys reproducibly from laptop to production. The project demonstrates full-stack data product skills with a sustainability edge: streaming ingestion, analytics that translate raw telemetry into operational decisions, and reporting rigorous enough to stand up to regulatory scrutiny.

transportationdockermongodb+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