Since 2012, our Player Safety – Early Detection System (PS-EDS) provides data that alerts our Responsible Gambling team if a customer shows signs of harmful behaviour. Combined with technical solutions, our team of Responsible Gambling analysts works on follow-up calls after automated detection by PS-EDS.  

How it works – our methodology 

Kindred and leading researchers have for years worked in tandem to develop an approach that can accurately identify harmful gambling behaviour. We have explored various scientific methods over the years and are now confident that we have found a suitable one to use for Kindred’s inhouse player monitoring system, Player Safety – Early Detection System (PS-EDS). 

The PS-EDS technology applies an algorithm based on the fifth edition of a well-known mental health classification model called the Diagnostic and Statistical Manual of Mental Disorders (DSM-5). DSM-5 is, more specifically, a diagnostic criteria documentation that allows us to take behavioural indicators into account. Simply put, each indicator of harmful behaviour is translated into corresponding data points. 

The behavioural data points are blended with complementary financial data, in total PS-EDS takes 27 features into consideration. By combining DSM-5, web analytics and risk calculations, the PS-EDS has evolved and is today allowing for even better detection of harmful gambling online. 

To increase transparency behind the thinking that led to the new version of PS-EDS, we have published a research paper that was thoroughly peer reviewed, which describes the thinking behind PSEDS. Further papers are planned to increase transparency and analysis on the system. 


Putting our system into practice  

Combined with technical solutions, our team of Responsible Gambling analysts works on follow-up calls after automated detection by PS-EDS. For each customer detected, they 

profile the online gambling behaviour, determine the risk level, and advise on 

harm-reduction measures, keeping in mind that each player is different. This ensures assistance is in line with the risk level. Once a customer has had an automated detection, that becomes the baseline to proceed from. Our team contacts the customer to manage, for example, deposit limits or how to self-exclude from problematic play, so each player can make their own decision about changing behaviour. If a customer is detected showing low risk, we use an automated response. In the case of medium risk, we take a more tailored human approach, and for high risk, we apply an active approach. 

Our assistance packages need to suit the general gambling and entertainment culture in each of our markets. We always offer what local gambling regulations require or recommend, and often go further, offering permanent self-exclusion and, in severe cases, closing the account ourselves. For younger players (18-24-year-olds), we increase the use of control tools and tailor our approach to include education on responsible gambling.  

  Low/moderate risk High risk
Criteria Player 1 Player 2
Loss of control
Score (out of 8) Risk indcators < 6 Risk indcators ≧ 6


Guiding principles – understanding PGSI and DSM-5 

Our player monitoring system, PS-EDS is all about reaching out to players before a harmful behavior is established. The system combines the principles of PGSI and DSM-5, which we introduce in more detail below. 

Problem Gambling Severity Index (PGSI)

In most research and diagnostic papers, the Problem Gambling Severity Index (PGSI) is used when identifying gambling disorder. This is a nine-item scale which is widely used to measure the gambling problem severity in the general population (Currie, Hodgins & Casey, 2013). This scale is known for having high internal reliability and good item-response characteristics (Orford et al., 2009). 

The PGSI defines four player types being the non-problem, low-risk, moderate-risk, and problem players. This classification is achieved through the following nine items:

  1. Have you ever bet more than you could really afford to lose?
  2. Have you needed to gamble with larger amounts of money to get the same feeling of excitement?
  3. Have you gone back another day to try to win back the money you lost?
  4. Have you borrowed money or sold anything to get money to gamble?
  5. Have you felt that you might have a problem with gambling?
  6. Have you felt people criticised you betting or told you that you had a gambling problem, regardless of whether you thought it was true?
  7. Have you felt guilty about the way you gamble, or what happens when you gamble?
  8. Has your gambling caused you any health problems, including a feeling of stress or anxiety?
  9. Has your gambling caused any financial problems for you or your household?

For each question, the player is given the following options to answer: Never, Sometimes, Most of the Time, and Always. Depending on the answer the player gives, there is a score attained to each answer: Never is equal to 0, Sometimes is equal to 1, Most of the Time is equal to 2 and Always gives a score of 3.

Depending on the final score that the player would achieve from answering these questions, this would correspond to the following classifications depending on the final score achieved: (i) social player (score 0), (ii) low-risk player (1-2), (iii) moderate-risk player (3-7), and (iv) high-risk player (8 or more). According to the PGSI, these classifications may be further interpreted through the following probably life consequences:

  • Social player corresponds with someone who would have not experienced any problems in the last year.
  • Low-risk player corresponds with someone who would have experienced one or two minor problems related to their gambling.
  • Moderate-risk player would be experiencing some problem related to their gambling.
  • High-risk player would be a person whose gambling may be dependent and is experiencing a substantial level of gambling related problems.

Ferris, J., and Wynne, H. J. (2001). The Canadian Problem Gambling Index. Final Report. Ottawa: Canadian Centre on Substance Abuse.

Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM 5)

The Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM 5) is also a diagnostic criteria documentation which is based on similar criteria as the PGSI mentioned above. According to the DSM 5, a diagnosis of gambling disorder requires at least four of the following criteria during the past year:

  • Needs to gamble with increasing amounts of money to achieve the desired excitement.
  • Is restless or irritable when attempting to cut down or stop gambling.
  • Has made repeated unsuccessful efforts to control, cut back, or stop gambling.
  • Is often preoccupied with gambling (e.g. having persistent thoughts of reliving past gambling experiences, handicapping, or planning the next venture, thinking of ways to get money with which to gamble).
  • Often gambles when feeling distressed (e.g. helpless, guilty, anxious, depressed).
  • After losing money gambling, often returns another day to get even (“chasing” one’s losses).
  • Lies to conceal the extent of involvement with gambling.
  • Has jeopardized or lost a significant relationship, job, or educational or career opportunity because of gambling.
  • Relies on others to provide money to relieve desperate financial situations caused by gambling


Related content