Floqsta AI-enabled algorithms intelligently match travelers into groups and trips based on shared interests, personality and group compatibility.
Floqsta brings the power of AI and machine-learning to enrich travel experience by being matched with amazing travel experiences and people that have similar interests and passions. We utilise travel preferences and learn from customer profiles and interactions on how to intelligently offer a choice of compatible floqs to join.
The platform senses demand and preferences for travel and applies a group social compatibility concept to intelligently form and curate travel groups. Automated creation of trips & groups, unconstrained by manual postings, facilitates volume and fluidity in the platform.
Floqsta is built on an NLP (Natural Language Processing)foundation, which learns from internal and external data to bring together users with compatible personalities and shared interests. The platform dynamically forms travel groups, called floqs, based on its proprietary group compatibility scoring and interaction propensity.
The intelligence in Floqsta will gradually learn more over time about what makes great travel companions. As a result, Floqsta will become more and more accurate in offering amazing travel opportunities and connecting you with like-minded people that best match your travel style.
Multiple layers of intelligence
An NLP (Natural Language Processing) foundation — unsupervised machine learning initially acting on 3rd party data to determine proximity between words and descriptors in order to understand similar interests.
Floq Orchestration & Display Optimization
Leveraging the scoring from the floq forming algorithms, these components apply further intelligence to optimize the presentation of floqs to the users.
Supervised machine learning, predicting probability by processing user profiles and messages, topics and semantic similarity and interaction history.
Floq Forming algorithms
Delivering a compatibility rating between users and potential floqs initially using logistical regression models and extending to deeper learning models in future.
Travel experiences and activities are contextually offered to the group based on trip purpose & group preferences enabling bond through common interests. The platform derives implicit personality traits based on activities users enjoy, as an input to the matching system.