INSIGHT BETBY
Sergey Tsukanov Chief Product Officer Betby
FORMATION OF AI LABS
AI Labs is a new project that began only a few months ago, with the understanding at the project’s core that AI is going to be a significant part of the betting industry's future. As such, we have decided to silo off AI-related research from any other ideas we're pursuing to ensure we continue to gain momentum in this field and avoid competition for internal resources.
Betby comprises many developers who all have plenty of ideas and cool features they want to implement. To avoid mixing up the two roadmaps we decided to create AI Labs. ICE will be an important milestone for AI Labs where we will publicly launch and share some of the projects we have in the works.
RECOMMENDER SYSTEM
Our recommender system is a very big project for Betby. Tis technology is totally new to the industry. When customers are placing bets, we are accumulating history, revealing patterns on what events they want to place bet on, what markets are preferable depending on their history and what sports events are happening right now.
Te system combines all these factors with what events operators offer markets on and what clients want to promote to give players a personalised experience and advise on what bets they could potentially be interested in.
Te bigger picture of all this is that we want to have the whole sportsbook fully personalised for players. Te recommender system will be one of the tools which Betby will be launching during ICE London.
Tere is also a new project in the works that would feed in well with the recommender system called Betting Tips aimed to provide contextual text information around betting events.
For example, if Manchester United are playing Chelsea the player will be receiving detailed snippets of information based on the historical data of the teams themselves. For instance, we can say that Team A would usually score three goals in this fixture or that Team B have scored over two goals per match over the last five games in the Premier League.
CHURN AND LTV PREDICTION
Churn and LTV prediction is a machine learning technology we felt was needed to fill in the gap
We created an alert system last year in collaboration with our risk management team. The system monitors what players are doing daily and identifies suspicious activity from players automatically. Based upon this concept, we made a first version of a notification system with predefined rules. Then we started gathering feedback, removing alerts that weren't useful, adding others that were and in doing so improved our model.
between what we are doing now and what we want to achieve. Tis is the first step on that path by giving our operators and clients the opportunity to predict the expected risk of losing players. Tis LTV then helps them to segment based on expecting monetary value from these players.
Tese are tools that are currently being used in the back office, but will be officially launched in London, and we are regularly receiving positive feedback from our partners. First impressions are very good, nonetheless we have a big list of features that we want to improve and add. Tis project is going to be a long-term project, with continuous improvements to the tools itself, and have its own dedicated roadmap.
RISK MANAGEMENT AUTOMATION
We created an alert system last year in collaboration with our risk management team. Te system monitors what players are doing daily and identifies suspicious activity from players automatically. Based upon this concept, we made a first version of a notification system with predefined rules. Ten we started gathering feedback, removing alerts that weren't useful, adding others that were and in doing so improved our model.
Tis system is evolving into a fully automatic risk management system – an AI risk manager tool. Innumerable tests carried from our end indicate that currently the tool covers nearly 99 per cent of all potential cases that were previously only identified manually.
BACKOFFICE BUSINESS INTELLIGENCE CHATBOT
Chatbot is a project that somewhat was started as as we wanted to explore the opportunities of how we can apply ChatGPT technologies and large language models in betting. Instead of having one report that is generated by manually filtering out vasts amount of data, with this BI chatbot tool operators can talk to their database and ask very specific questions in relation to scenarios which they want to acquire data
about, such as the comparison of active players to previous periods or an analysis of trends.
It has significant potential, and we are excited thinking about how to apply this technology at user level so even bettors themselves can talk to the sportsbook. Tere are thousands of sports events every day featuring hundreds of markets - many of which users don't understand properly. Tis kind of assistant can help them understand, find events they want to place a bet on and explain how markets work, potentially to give some tips, and so forth.
PERSONAL ENJOYMENT
Te most interesting project for me personally is the recommender system and the Chatbot assistant because I enjoy finding out the actual value that can be extracted from technologies being hyped up such as large language models. Everyone is talking about them and taking on the challenge of trying to make money from them is exciting and challenging because no one knows exactly how it works, how to approach them, how to adopt the new technology to a particular use case.
Te recommender system is a major topic in machine learning, one that's been well studied and approached from lots of angles with fresh ideas. Technically, this project is interesting and exciting from an implementation perspective because a sportsbook is very different to Netflix because odds are changing, events are changing, everything is constantly changing. It's an incredibly dynamic environment.
BIGGER PICTURE
Whilst we're discussing them in this interview separately, we try to not separate all these projects internally but combine them. For example, if there is a recommender system, there is a churn prediction. If we can automatically predict the churn of players, then we can automatically suggest the best events for others player to bet on certain events. Tese are all components of a bigger system that I hope one day will all come together.
Chatbot is a project that somewhat was started as as we wanted to explore the opportunities of how we can apply ChatGPT technologies and large language models in betting. Instead of having one report
that is generated by manually filtering out vasts amount of data, with this BI chatbot tool operators can talk to their database and ask very specific questions in relation to scenarios.
WIRE / PULSE / INSIGHT / REPORTS P105
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137 |
Page 138 |
Page 139 |
Page 140 |
Page 141 |
Page 142 |
Page 143 |
Page 144 |
Page 145 |
Page 146 |
Page 147 |
Page 148 |
Page 149 |
Page 150 |
Page 151 |
Page 152 |
Page 153 |
Page 154 |
Page 155 |
Page 156 |
Page 157 |
Page 158 |
Page 159 |
Page 160 |
Page 161 |
Page 162 |
Page 163 |
Page 164 |
Page 165 |
Page 166 |
Page 167 |
Page 168 |
Page 169 |
Page 170 |
Page 171 |
Page 172 |
Page 173 |
Page 174 |
Page 175 |
Page 176 |
Page 177 |
Page 178 |
Page 179 |
Page 180 |
Page 181 |
Page 182 |
Page 183 |
Page 184 |
Page 185 |
Page 186 |
Page 187 |
Page 188 |
Page 189 |
Page 190 |
Page 191 |
Page 192 |
Page 193 |
Page 194 |
Page 195 |
Page 196 |
Page 197 |
Page 198 |
Page 199 |
Page 200 |
Page 201 |
Page 202 |
Page 203 |
Page 204 |
Page 205 |
Page 206 |
Page 207 |
Page 208 |
Page 209 |
Page 210 |
Page 211 |
Page 212
