DETECTING CHANGE INSTEAD OF VOLUME


One of the most important lessons in churn prediction is that absolute numbers rarely tell the full story. A user placing two bets per day might appear inactive compared to a high-volume bettor, but highly engaged relative to their own history. What matters the most here is behavioural deviation.


For this reason, BETBY’s churn models focus on how user behaviour shifts over time, using relative indicators — rather than absolute values — such as:


u Betting frequency (last three days vs 30-day baseline) u Stake volatility


u Session truncation (sessions ending earlier than usual) u Market abandonment (views without bets)


u Loss-adjusted disengagement (losing streak x activity slope) u Time since last bet relative to typical activity pattern


Tese features allow the system to detect behavioural drift early. For example, a user who normally places five live bets per session but suddenly places one and exits early, generates a stronger churn signal than a consistently low-volume bettor.


Basic systems miss this entirely because they measure inactivity instead of deviation.


PRODUCTION-READY MODELLING


Once features are engineered, machine learning models estimate the probability that a user will churn within a specific time horizon, given their current behavioural state.


Te production stack typically includes: u


Gradient Boosted Trees u Separate models per churn horizon u Churn likelihood score instead of a fixed yes/no classification


Tis is particularly important during the World Cup, where behaviour is highly volatile. Tat’s because emotional losses, traffic spikes, and irregular session timing can confuse simplistic rule-based systems. Meanwhile, proper ML models absorb volatility rather than


However, understanding when users are at risk is only part of the picture. In the third and final article of this mini-series, we will examine how player segmentation evolves during the World Cup, and why temporary “event modes” become essential in delivering the right experience to the right user at the right time.


39


Te World Cup compresses acquisition, engagement, and disengagement cycles into a matter of weeks, meaning platforms that rely on delayed signals only realise users have left after it is too late.


By monitoring and predicting well in advance behavioural change rather than waiting for inactivity, BETBY’s AI-driven system surfaces risk while there is still time to respond. Tis approach respects user behaviour, avoids unnecessary pressure on operators, and supports more sustainable engagement during major tournaments.


overreacting to it, and the result is a continuously updated risk spectrum instead of a delayed “inactive” tag.


FROM PREDICTION TO ACTION


Nevertheless, prediction alone has limited to zero value without integration. Tat’s why BETBY’s churn probabilities feed directly into UX logic and operator strategy. Depending on their goal, operators may prioritise:


u


Short-term reactivation during the tournament (three–seven day risk)


u Longer-term retention beyond the final (14–30 day risk)


A user trending toward short-term churn after a losing streak may see simplified markets and confidence-restoring content. On the other hand, a bettor moving toward long-term disengagement may need a more structured retention approach, always aligned with responsible gaming guidelines. In practical terms, this means the same intelligence can support different strategies.


In contrast, basic AI systems often rely on static CRM triggers activated only after inactivity occurs. Te problem with this is that, by the time the system reacts, user attention has often shifted elsewhere and the bettor is gone.


COMPETITIVE ADVANTAGE DURING MAJOR EVENTS


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