Learn How AI-Powered Sports Software Helps Event Organisers

Leveraging AI-powered sports software with our core Aktivebot chatbot, the goal was to create an automated assistant available 24/7 to reduce time and effort needed by event organisers to respond to event enquiries whilst still providing an easy way to contact the events team if necessary.

The Challenge

The Saddleback Fred Whitton Challenge is a charity event in honour of the late Fred Whitton consisting of a 112-mile charity sportive around the Lake District with over 2,000 riders and 5,000 applications. The event has operated since 1999 and maintains substantial social media engagement with 4,000+ Facebook followers where organisers fielded numerous inquiries through messaging features.

Project Objectives

The sports software project aimed to deploy an intelligent chatbot handling event queries around the clock, integrated within Facebook Messenger. The solution needed to maintain user experience quality while enabling direct organiser contact when necessary.

Chatbot Capabilities

The conversational system understood natural language and responded to inquiries including: event descriptions, deferral requests, race pack timing, GPS file requests, merchandise purchasing, organiser contact preferences, and results availability. The chatbot referenced website information to function alongside existing resources.

Technology Stack

Implementation utilised Google Dialogflow to provide the NLP engine and Google Firebase for the fulfilment hosting. The webhook enabled complex response computation, including retrieving historical participant results from databases. Facebook UI elements displayed rich content for merchandise details and direct shop linking.

Conversation Design Process

Initial Training Data: The team imported pre-created sports event intents from Aktivebot, analysed FAQ data from the steering committee, and reviewed historical Facebook questions to inform conversational scripts.

Question Categories: Frequently asked topics encompassed registration details (deferrals, availability, waiting lists), merchandise inquiries, ride specifics (routes, road closures, apparel recommendations), and post-event information (results, photos, future dates).

Iterative Refinement: The training process involved continuous improvement, with system logs reviewed multiple times daily. This ongoing learning cycle prepared the chatbot for subsequent events with easily updatable event-specific details.

Results and Performance

The chatbot demonstrated significant participant engagement, attributed to providing timely information the website alone couldn't deliver quickly, such as road closure updates and route modifications. Initial success rate reached approximately 60%, with expectations to achieve an 80% target through extended training with future 2019 events.

Response was positive overall. The system gracefully handled unmatched intents and successfully transferred users requesting direct organiser assistance. One steering group member noted: "I'm impressed with the chatbot, it seemed to work well. I think it is a good source of help and with it learning as it goes along it would answer lots of questions going forward."

Future Development

Additional improvements could incorporate system integration expansion and push notification functionality. Website integration through chat widgets was identified as potentially increasing engagement beyond Facebook Messenger deployment.