Mini Project
Data Science
Personal Finance Analytics
Statement parsing, auto-categorisation and spend forecasting
- Python
- Pandas
- Prophet
- Streamlit
- +2
₹2,299₹3,999
4.5/198 reviews
Data Science · Major Project
Illegal Fishing Detection from Vessel Tracks
Classifies fishing behaviour from AIS vessel tracking data
3-4 weeks build
Overview
Ships broadcast their position through AIS, and fishing leaves a recognisable pattern of slow, looping movement. Using labelled track data published by Global Fishing Watch, this kit engineers speed, heading and turning features over time windows and trains models to classify fishing activity, then flags fishing inside protected zones on an interactive map.
What makes it stand up
- 01Labelled AIS tracks from Global Fishing Watch public data
- 02Windowed speed, heading and turn-rate features
- 03Gradient boosting compared with a random forest baseline
- 04Protected-zone overlay flagging suspicious fishing
- 05Precision, recall and per-gear-type results in the report
Module breakdown
- 01
Ingestion
AIS track loading, cleaning and resampling.
- 02
Features
Rolling motion statistics per vessel window.
- 03
Models
Random forest and XGBoost with cross-validation.
- 04
Zones
Geofence checks against protected-area polygons.
- 05
Map app
Streamlit map of tracks, predictions and flags.
After this, you will be able to
- Explain what AIS data contains and its gaps
- Defend your feature windows and validation split
- Demo a vessel track flagged inside a protected zone
Technology stack
- Python
- Pandas
- scikit-learn
- XGBoost
- Streamlit
- Level
- Major Project
- Domain
- Data Science
- Build time
- 3-4 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support