Focused on POI Recommendation

CAPRI is a specialized framework for evaluating and benchmarking several state-of-the-art POI recommendation models. It is equipped with state-of-the-art models, algorithms, well-known datasets for POI recommendations, and multi-dimensional evaluation criteria.

Open To Contribute

The framework is distributed under the GPL-v3 license and can be downloaded or cloned from GitHub. It is simple to add new models, datasets, and metrics; we welcome academics and developers who aim to contribute to the framework’s enhancement

Reproducible Results

CAPRI is an open source recommendation framework implemented in Python 3 that is suitable for practical experimentation and reproducibility study. In the recent future, the framework will cover a wider range of datasets and models, along with other robust evaluation metrics.

CAPRI is focused on POI Recommendation!

Why do we need a specialized framework for POI recommendation?

The majority of current frameworks are general-purpose and do not prioritize domain-specific recommendation models, such as context-awareness. In contrast, CAPRI focuses on the POI domain and aims to provide researchers with all the necessary resources in this field.

What makes CAPRI unique compared to other recommendation frameworks?

In contrast to the introduced frameworks, CAPRI is only focused on the Point-of-Interest domain and tries to provide all the tools needed for this field.

What POI-specific items can be found in CAPRI?

In the current version of the framework, we have provided modified versions of three popular check-ins datasets, including Gowalla, Yelp, and Foursquare. Also, the models implemented in our framework are GeoSoCa, LORE, and USG. CAPRI is highly compatible with a range of evaluation metrics as well.