A machine learning perspective on responsible gambling

Arman Hassanniakalager, Philip W.S.Newall

Research output: Contribution to journalArticle

Abstract

Gamblers are frequently reminded to ‘gamble responsibly’. But these qualitative reminders come with no quantitative information for gamblers to judge relative product risk in skill-based gambling forms. By comparison, consumers purchasing alcohol are informed of product strength by alcohol by volume percentage (ABV%) or similar labels. This paper uses mixed logistic regression machine learning to uncover the potential variation in soccer betting outcomes. This paper uses data from four bet types and eight seasons of English Premier League soccer, ending in 2018. Outcomes across each bet type were compared using three betting strategies: the most-skilled prediction, a random strategy and the least-skilled prediction. There was a large spread in betting outcomes, with, for example, the per-bet average loss varying by a factor of 54 (from 1.1% to 58.9%). Gamblers’ losses were positively correlated with the observable betting odds across all bets, indicating that betting odds are one salient feature that could be used to inform gamblers about product risk. Such large differences in product risk are relevant to the promotion of responsible gambling.
LanguageEnglish
Pages1-26
Number of pages26
JournalBehavioural Public Policy
Early online date29 Apr 2019
DOIs
StatusPublished - 29 Apr 2019

Keywords

  • social and behavioural sciences
  • Consumer psychology
  • nudges

Cite this

A machine learning perspective on responsible gambling. / Hassanniakalager, Arman; W.S.Newall, Philip .

In: Behavioural Public Policy, 29.04.2019, p. 1-26.

Research output: Contribution to journalArticle

@article{8ab01633173b40e68a1737fe6ed7b215,
title = "A machine learning perspective on responsible gambling",
abstract = "Gamblers are frequently reminded to ‘gamble responsibly’. But these qualitative reminders come with no quantitative information for gamblers to judge relative product risk in skill-based gambling forms. By comparison, consumers purchasing alcohol are informed of product strength by alcohol by volume percentage (ABV{\%}) or similar labels. This paper uses mixed logistic regression machine learning to uncover the potential variation in soccer betting outcomes. This paper uses data from four bet types and eight seasons of English Premier League soccer, ending in 2018. Outcomes across each bet type were compared using three betting strategies: the most-skilled prediction, a random strategy and the least-skilled prediction. There was a large spread in betting outcomes, with, for example, the per-bet average loss varying by a factor of 54 (from 1.1{\%} to 58.9{\%}). Gamblers’ losses were positively correlated with the observable betting odds across all bets, indicating that betting odds are one salient feature that could be used to inform gamblers about product risk. Such large differences in product risk are relevant to the promotion of responsible gambling.",
keywords = "social and behavioural sciences, Consumer psychology, nudges",
author = "Arman Hassanniakalager and Philip W.S.Newall",
year = "2019",
month = "4",
day = "29",
doi = "10.31234/osf.io/sxbaq",
language = "English",
pages = "1--26",
journal = "Behavioural Public Policy",
issn = "2398-063X",
publisher = "Cambridge University Press",

}

TY - JOUR

T1 - A machine learning perspective on responsible gambling

AU - Hassanniakalager, Arman

AU - W.S.Newall, Philip

PY - 2019/4/29

Y1 - 2019/4/29

N2 - Gamblers are frequently reminded to ‘gamble responsibly’. But these qualitative reminders come with no quantitative information for gamblers to judge relative product risk in skill-based gambling forms. By comparison, consumers purchasing alcohol are informed of product strength by alcohol by volume percentage (ABV%) or similar labels. This paper uses mixed logistic regression machine learning to uncover the potential variation in soccer betting outcomes. This paper uses data from four bet types and eight seasons of English Premier League soccer, ending in 2018. Outcomes across each bet type were compared using three betting strategies: the most-skilled prediction, a random strategy and the least-skilled prediction. There was a large spread in betting outcomes, with, for example, the per-bet average loss varying by a factor of 54 (from 1.1% to 58.9%). Gamblers’ losses were positively correlated with the observable betting odds across all bets, indicating that betting odds are one salient feature that could be used to inform gamblers about product risk. Such large differences in product risk are relevant to the promotion of responsible gambling.

AB - Gamblers are frequently reminded to ‘gamble responsibly’. But these qualitative reminders come with no quantitative information for gamblers to judge relative product risk in skill-based gambling forms. By comparison, consumers purchasing alcohol are informed of product strength by alcohol by volume percentage (ABV%) or similar labels. This paper uses mixed logistic regression machine learning to uncover the potential variation in soccer betting outcomes. This paper uses data from four bet types and eight seasons of English Premier League soccer, ending in 2018. Outcomes across each bet type were compared using three betting strategies: the most-skilled prediction, a random strategy and the least-skilled prediction. There was a large spread in betting outcomes, with, for example, the per-bet average loss varying by a factor of 54 (from 1.1% to 58.9%). Gamblers’ losses were positively correlated with the observable betting odds across all bets, indicating that betting odds are one salient feature that could be used to inform gamblers about product risk. Such large differences in product risk are relevant to the promotion of responsible gambling.

KW - social and behavioural sciences

KW - Consumer psychology

KW - nudges

U2 - 10.31234/osf.io/sxbaq

DO - 10.31234/osf.io/sxbaq

M3 - Article

SP - 1

EP - 26

JO - Behavioural Public Policy

T2 - Behavioural Public Policy

JF - Behavioural Public Policy

SN - 2398-063X

ER -