Askblu.ai founder and CEO Dominique Busso on using A.I. solutions to improve player retention

"Traditional solutions like A/B testing are tedious and do not give optimised results"

Askblu.ai founder and CEO Dominique Busso on using A.I. solutions to improve player retention

As A.I. technologies evolve, the way we use them in-game development is also changing.

Throughout the month of March, PG.biz will be running a series of articles all about using A.I. in development, marketing and beyond. We'll be speaking with companies and individuals in the gaming space, alongside A.I.-focused firms using the tech to up their game.

This month’s “A.I. in the Gaming Sector” theme is brought to you by Ludo, the world’s first A.I. platform for games concept creation. Ludo is a real ‘gamestorming’ tool designed to turbocharge your creative power through A.I. Whether you’re a solo developer/designer, studio, hobbyist or student, Ludo acts as your trusty assistant helping to “gamestorm” great new game concepts.

This time we're chatting with Dominique Busso, founder and CEO of machine learning platform Askblu.ai. The company utilises A.I. solutions in order to improve user retention with real-time player personalisation. This means the game will adjust itself to suit a user's playstyle making them more inclined to keep going if they're struggling. We caught up with Busso to discuss the benefits of this, as well as the overall evolution of how A.I. is being used in game development.

PocketGamer.biz: Can you give us a brief overview of Askblu and the services you provide?

Dominique Busso: Askblu.ai is a SaaS platform designed to deliver real-time player personalisation for mobile games. Askblu puts Machine Learning at work to enhance players’ experience, retention and LTV. The platform offers:

  • A Data-Driven Difficulty Analysis, to help studios balance their games during soft-launched
  • A Real-Time (in-game) Difficulty Personalisation solution, to increase retention and LTV
  • A Real-Time (in-game) Ad Pressure Personalisation solution, to maximise ad revenues.

When people think A.I. in gaming, they usually think of traditional elements such as programming NPCs. What other aspects of game dev can be improved with A.I.?

Yes, A.I. has been used traditionally for NPCs. But today’s technology allows us to process players' behaviour data in real-time, learn from the massive amount of data, and provide innovative services like real-time personalisation and player-based data analysis.

For instance, data-driven difficulty analysis can tell game designers, for each stage in a game, whether the difficulty is optimum for the global player audience, or if the stage should be easier or harder.

Real-time difficulty personalization allows game studios to keep more players in their games (cognitive flow: frustration and boredom leads to churn). It also helps keep live games tuned when the acquisition channels are changed - the game’s audience of players might change, for example.

Please note that “behaviour” data is totally anonymous data (we don’t need to know who the players are, but what they do in a game), and does not use the now-famous “IDFA”.

Can you explain how A.I. works with in-game personalisation?

The studio integrates our SDK in the game (our SDK is as simple as possible, made for game designers, not data engineers). When a player plays, Askblu.ai receives the behaviour events: start a session, start a stage, etc. These events are processed on our platform in real-time, becoming “player features”. For each game, a Machine Learning model is updated every day with these features.

When a player decides to start a stage, a request is sent to Askblu.ai, which answers “keep the default difficulty” or ”make it easier” or ”make it harder”. the difficulty can therefore be adapted for the player.
Each answer from Askblu.ai is personalised, for one player, at the time of the request, based on frustration/boredom prediction. 

Game designers want to design games, not neural-networks. A.I. will help them better understand their players and adapt to their diversity.

How have A.I. solutions changed game development in the 5 years?

I think that the changes are just starting now. Many studios are struggling to tune and balance their games. Traditional solutions like A/B testing are tedious and do not give optimised results (taking into account error margins). In the next few years, machine learning (based on players’ behaviour data) will help game designers and monetisation managers a lot more, while enhancing the players’ experience.

Big studios and publishers are already working on this. Our goal is to allow small, mid-sized studios and publishers to benefit from this revolution.

What advice would you give to companies that introduce A.I. solution to their overall strategy, but are put off by the complexity and terminology?

Work with a SaaS solution like ours, where the whole data pipeline, processing, and inferring, is available at scale with no upfront costs. 10 years ago, many studios were developing their own analytic solutions. Today there are many affordable and efficient analytic SaaS solutions available and widely used. I think that it will be the same with A.I. solutions, all the more because compared to analytic tools, A.I.-based platforms are more complex, even more costly to set up (with real-time/scalable serverless solutions), and require highly specialised staff (data engineers, data scientists).

Game designers want to design games, not neural-networks. A.I. will help them better understand their players and adapt to their diversity.

What is the next big step in A.I. for game development?

At a time where UA is more complicated (consent for sharing IDFA), mobile game studios and publishers are putting more efforts into retaining those hard-to-acquire players, and the “Internet of Behaviours” is the next frontier (real-time machine learning and predictive analysis based on players’ behavioural data).

“Packaging” this A.I. technology for easy SaaS delivery to businesses is also a big step, made possible by the widespread use of server-less technologies like AWS.

The month of “AI In The Gaming Sector” is sponsored by Ludo, the ‘gamestorming’ tool to celebrate the role of AI and machine learning in creative industries. Ludo is the AI tool revolutionising games creation by using machine learning and natural language processing to develop game concepts 24 hours a day and democratising games creation.

Ludo is built on a database of close to a million games and is constantly learning and evolving. When asked to find a new game idea, based on intuitive keyword searches, Ludo returns almost immediately with multiple written game concepts, artwork and images. To find out more and try Ludo head to www.askludo.ai.


Danielle Partis is editor of PocketGamer.biz and former editor of InfluencerUpdate.biz. She was named Journalist of the Year at the MCV Women in Games Awards 2019, as well as in the MCV 30 under 30 2020. Prior to Steel Media, she wrote about music and games at Team Rock.