This repository contains the source code, experimental results, and analysis for our project on data mining and prediction using human mobility data in Japan. The project covers three major tasks: frequent pattern discovery, sequential pattern mining, and next-location prediction using deep learning techniques.
This project explores various data mining techniques to analyze and predict human mobility patterns using real-world location data collected in Japan.
The key objectives and tasks include:
- Frequent POI Identification
Applied the Apriori algorithm to discover frequently visited Points-of-Interest (POIs) across the dataset. - Mobility Pattern Mining
Implemented the Generalized Sequential Pattern (GSP) algorithm to identify common movement sequences among residents. - Next Location Prediction
Developed a Long Short-Term Memory (LSTM) model to forecast a user’s next location based on historical movement trajectories.
For each task, we integrated optimized algorithms, implemented detailed pre-processing pipelines, and evaluated our methods based on accuracy and efficiency.
| Name | Task | GitHub |
|---|---|---|
| Brandon Jang Jin Tian | Next Location Prediction | @BrandonJang |
| Chung Zhi Xuan | Data Preprocessing, GSP Sequential Pattern Mining | @spaceman03 |
| Ting Ruo Chee | GSP Sequential Pattern Mining | @ruochee723 |
| Yau Jun Hao | Frequent POI Identification | @ |