Semantic Trajectories for Jakarta from Foursquare Check-Ins

Massive-STEPS-Jakarta is a large-scale dataset of semantic trajectories derived from Foursquare Open Source Places and the Semantic Trails Dataset. It contains check-in data from Jakarta, Indonesia, and is intended for research in trajectory prediction and urban modeling. The dataset was created by the CRUISE Research Group and was last updated in September 2025.

Use Cases

• Predict next POI check-in from user trajectory sequences using timestamps and location IDs.
• Model urban activity patterns by analyzing the frequency and sequence of check-ins across different city areas.
• Train semantic trajectory embedding models using user ID, POI category, and temporal features.
• Evaluate POI recommendation algorithms based on historical check-in data and user preferences.

Strengths

• Part of a large-scale collection spanning 15 cities across 10 countries.
• Derived from established sources like Foursquare Open Source Places and the Semantic Trails Dataset.

Limitations

• Specific row count, column names, and temporal coverage for the Jakarta subset are not provided.
• Potential geographic bias as data is sourced from a specific platform's user base.

Provenance

Source

Derived from the Semantic Trails Dataset and Foursquare Open Source Places.

Collection Method

Aggregated from check-in data.

Freshness

Last updated in September 2025.

Geography

Jakarta, Indonesia.