Difference between revisions of "AY1516 T2 Sport Betting Project Overview Proposal"

From Analytics Practicum
Jump to navigation Jump to search
(Created page with "<br> <font face="Century Gothic"> {| style="background-color:#FFFFFF; color:#007BBD padding: 5px 0 0 0;" width="100%" cellspacing="0" cellpadding="0" valign="top" border="0" |...")
 
 
(2 intermediate revisions by 2 users not shown)
Line 1: Line 1:
<br>
 
<font face="Century Gothic">
 
{| style="background-color:#FFFFFF; color:#007BBD padding: 5px 0 0 0;" width="100%" cellspacing="0" cellpadding="0" valign="top" border="0" |
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; border-left:2px solid #007BBD; background:#007BBD; text-align:center;" width="20%" |
 
[[AY1516_T2_Sport_Betting_at_Singapore_Pools|<font face ="Century Gothic" color="#FFFFFF"><strong>THE SPONSOR</strong></font>]]
 
| style="border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD;" width="1%" | &nbsp;
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px #007BBD; border-top:2px solid #007BBD; background:#007BBD; text-align:center;" width="20%" | 
 
[[AY1516_T2_Sport_Betting_at_Singapore_Pools_Team|<font  face ="Century Gothic" color="#FFFFFF"><strong> THE TEAM </strong></font>]]
 
| style="border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD;" width="1%" | &nbsp;
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#FFFFFF; text-align:center;" width="20%" | 
 
[[AY1516_T2_Sport_Betting_at_Singapore_Pools_Project_Overview_Proposal|<font face ="Century Gothic" color="#007BBD"><strong> THE OVERVIEW</strong></font>]]
 
| style="border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD;" width="1%" | &nbsp;
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px #007BBD; border-top:2px solid #007BBD; background:#007BBD; text-align:center;" width="20%" |
 
[[AY1516_T2_Sport_Betting_at_Singapore_Pools_Project_Management|<font  face ="Century Gothic" color="#FFFFFF"><strong> THE MANAGEMENT </strong></font>]]
 
| style="border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD;" width="1%" | &nbsp;
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD; text-align:center;" width="20%" |
 
[[AY1516_T2_Sport_Betting_at_Singapore_Pools_Documentation|<font  face ="Century Gothic" color="#FFFFFF"><strong> THE DOCUMENTS </strong></font>]]
 
| style="border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD;" width="1%" | &nbsp;
 
| style="padding:0.3em; font-family:Helvetica; font-size:120%; border-bottom:2px solid #007BBD; border-top:2px solid #007BBD; background:#007BBD; text-align:center;" width="20%" |
 
|}
 
<br>
 
  
<!--Sub-Navigation-->
 
{| style="background-color:white; color:white ; border: 0px solid #007BBD; margin-left: auto; margin-right: auto;" width="800px" height=50px cellspacing="0" cellpadding="0" valign="top"  |
 
 
| style="padding:0 .3em;  solid #00000;  padding: 10px; text-align:center; background-color: grey; border: 1px solid grey; " width="33%" | [[AY1516_T2_Sport_Betting_at_Singapore_Pools_Project_Overview_Proposal| <font face = "Arial" color="white"><b>Proposal </b></font>]]
 
 
| style="padding:0 .3em;  solid #000000; text-align:center; border: 1px solid grey; " width="34%" | [[AY1516_T2_Sport_Betting_at_Singapore_Pools_Project_Overview_Midterm| <font face = "Arial" color="#101010"><b>Midterm</b></font>]]
 
 
| style="padding:0 .3em;  solid #000000; padding: 10px; text-align:center; border: 1px solid grey;" width="33%" | [[AY1516_T2_Sport_Betting_at_Singapore_Pools_Project_Overview_Final| <font face = "Arial" color="#101010"><b>Final</b></font>]]
 
 
|
 
 
|}
 
 
<!--END OF Sub-Navigation-->
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Aim & Objectives</font></div></div>==
 
 
The aim of our project is to allow Singapore Pools to better understand the gambling behaviours of their customers through the identification of gambling patterns, which can be unique across different clusters of individuals. Each cluster might have their own specific ways of splitting their bets, different churn rates, preference for a league, different decision making process, and ways of selecting their bet selections. Such behavioural patterns could possibly be linked back to certain demographics pertaining to the cluster, allowing us to further infer reasons behind their gambling habits, and hopefully could help us identify those irresponsible gamblers too. For the purpose of the project, the scope of our project is limited to the Sports Betting segment of customers who have opened betting accounts with Singapore Pools.
 
 
<center>
 
The overall objectives of our project are to:
 
 
<b>(1) Profile their existing pool of customers through clustering analysis
 
 
(2) Create a data visualization of the consumer betting activity
 
 
(3) Build a dashboard to visualize the profiling and data points
 
</b>
 
</center>
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Motivations</font></div></div>==
 
 
In today’s globalized world, the Internet has transformed the gambling environment into a multifaceted, non-physical, multi-platform, environment without boundaries. This presents loopholes for illegal gambling operators to enter the market and draw our customers away, into their unregulated arena that is susceptible to the creation of gambling addiction issues. 
 
 
Singapore Pools offers a safer outlet, one where players can bet responsibly, within their means. Attrition rates have be raising over the years, and this could meant that Singapore Pools’ customers are seeking other avenues to participate in gambling activities such as illegal online-gambling sites, which may lead to irresponsible betting. Therefore, within the next few years, our sponsor seeks to undertake a data-driven approach to promote responsible gambling by monitoring the player's’ betting behaviour and performance, in hopes of highlighting alarming patterns that could indicate signs of irresponsible gambling.   
 
 
Our sponsor has actually been collecting user data for the past several years, but has yet put it to good use. Just a year ago, Singapore Pools had set up a customer insights division to better understand their customers through the analysis of these user data and their first step towards a data-driven approach to promote responsible gambling was to understand the gambling behavioural patterns of their customers.
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Literature Review</font></div></div>==
 
 
Singapore has the highest spending on gambling per capita as reported by Global Betting and Gaming Consultants. In the 2014 NCPG (National Council on Problem Gambling) survey report, an estimated 44% of Singapore’s population have participated in gambling related activities in a one year period, compared to a 47% in their last survey in 2011. The amount of bet has also fallen, with about 90% of the surveyed spending less than $200 per month; and only a minute fraction of them (0.3%) gambled with large amounts of over $1000 each month. An alarming finding in this survey was that probable pathological gamblers are on the rise, with greater frequency of gambling (83% gambled once a week, as compared to 68% in 2011). Furthermore, this regular gambling habit was picked up at a younger age, with 17% gambling regularly before the age of 18 in comparison to a 5% in 2011.The rise of such phenomenon was the result of early exposure to online gambling, as such the need to regulate gambling content.
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">General Introduction to the Rules of Soccer Betting</font></div></div>==
 
 
In soccer betting, the customer places a wager on any of the selections under a specific bet type (e.g. home team to win, total number of goals in the match equals to 3). If the selection corresponds to the winning selection as declared by Singapore Pools, the customer will qualify for the winnings, which are based on the prevailing odds at the time the customer’s bets are placed.
 
 
<br/>
 
[[File:New-soccer-season-xl.jpg | 1000px]]
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Data</font></div></div>==
 
 
The dataset will be presented to us in the form of an Excel spreadsheet and each worksheet within the spreadsheet contains the entire purchase history of one player along with other recorded parameters. We will be given a dataset consisting of approximately 4,000 unique customer accounts with account activity details over a time period of three months. The time period spans from January to March, which coincides with the peak period of the different international soccer leagues, so as to ensure the high volume of betting activity for analysis.     
 
 
 
 
<center>The parameters in the dataset can be split into three distinct categories and include the following:
 
 
<b>1. Demographics of Players</b>
 
 
Customer Account No.
 
 
Gender
 
 
Date of Birth
 
 
Income Range
 
 
Type of Membership
 
 
Nationality
 
 
Account Opening Date
 
 
 
<b>2. Betting Activity</b>
 
 
Customer Account No.
 
 
Bet Date & Time
 
 
Bet Selection
 
 
Bet Type
 
 
Event Name
 
 
Event Code
 
 
Bet Amount
 
 
Bet Odds
 
 
Bet Start Time of Bet Event
 
 
 
<b>3. Top Up & Withdrawal Activity</b>
 
 
Customer Account No.
 
 
Transaction Date & Time
 
 
Transaction Type
 
 
Transaction Mode
 
 
Transaction Amount</center>
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Methodology & Work Scope</font></div></div>==
 
 
Our methodology and proposed work scope for this project are as follows:
 
 
(1) Data cleaning
 
 
(2) Data exploration
 
 
(3) Data transformation
 
 
(4) Cluster analysis & profiling
 
 
(5) Relationship cross analysis
 
 
(6) Creation of new player metrics
 
 
(7) Wireframe dashboard & select display parameters
 
 
(8) UX internal audit
 
 
(9) Client consultation on dashboard
 
 
(10) Application calculations & filtering
 
 
(11) Dashboard prototype I
 
 
(12) Dashboard testing & calibration
 
 
(13) Dashboard prototype II
 
 
(14) Dashboard final optimization
 
 
(15) Client user testing
 
 
<br>
 
<strong>First phase</strong> - Data cleaning and Data preparation
 
 
The first phase would be data cleaning; such steps would include: (1) filtering out non-Singaporean players for they are not Singapore Pools’ primary concern and would possibly skew the betting pattern; (2) filtering out one-off players who were only active for a brief period; (3) filtering out incomplete-data or empty fills if any.
 
 
<strong>Second phase</strong> - Data transformation
 
 
Data transformation then follows suit. With the given parameters, we will create new metrics (categorical data) for each player such as age and their socioeconomic standing (SES) - we can identify their age using their NRIC number, and their SES as a rough gauge of their assets on the basis of the real estate property they own. This new data formats would then be put into higher level analytical models and analysis.   
 
 
<strong>Third phase</strong> - Data analytics
 
 
We will proceed to leverage on analytical tools (i.e. SAS, SPSS) to create profiles and segments of various betting behaviours.
 
 
<strong>Fourth phase</strong> - Discovery of relationship
 
 
Based on the segmentation of the players, we will draw links between the demographics of each segment and the betting behavioural patterns.
 
 
<strong>Fifth phase</strong> - Wireframing and selecting display parameters
 
 
Next comes the designing the user-interface of the dashboard and visualization of data graphs for simple and pleasant viewing. The various viewing pages (for summary or visualize of specific data) will be implemented and the dashboard navigation paths will be planned for.   
 
 
<strong>Sixth phase</strong> - Building of dashboard for data visualization
 
 
Before inserting the parameters into the dashboard, we must once again carry out an overall transformation of data into readable CSV for bootstrapping to the dashboard prototype. We will be using either Tableau or D3.js to build the data visualization.
 
 
<strong>Seventh phase</strong> - Optimization of dashboard
 
 
Based on the feedback given during the mid-term reporting and by the client, we will implement modifications to the dashboard to ensure that the client’s requirements are met in this final phase of the project.
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Deliverables</font></div></div>==
 
 
(1) Mid-term report & presentation
 
 
(2) Final report & presentation
 
 
(3) Project poster
 
 
(4) Customized dashboard
 
<br>
 
 
==<div style="background: #007BBD; line-height: 0.3em; border-left: #007BBD solid 13px;"><div style="border-left: #45E98F solid 5px; padding:15px;"><font face ="Century Gothic" color= "white" size="5">Project Limitations & Assumptions</font></div></div>==
 
 
The data collected are only from players who use Singapore Pool’s phone betting service, and this only accounts for 5% of their entire pool of customers. The remaining 95% are anonymous players who make bets at Singapore Pools’ physical stall outlets. Given that this project outcome was meant as a precursor to help with the launch of Singapore Pools’ online betting system, their target audience would be more similar to those that are using the current betting lines service, hence this limited behaviour data we have are perfect to model those future online players.   
 
 
There is a lack of secondary data with regards to this niche field of research on gambling, in Singapore specifically. Without existing literature and data on Singaporean’s betting behaviour, we will not be able to compare the results from our profiling and verify the underlying reasons behind their betting patterns. The only secondary data that we can benchmark our data with is one report that studied a sample of Australian gamblers in the state of Victoria, hence we had to make the assumption that cross cultural differences would have little influence on how players of the different demographics in each country made betting decisions.
 
 
However, our chief priority would be to highlight gaps in the data that may possibly predict patterns of irresponsible gambling, and not to infer the underlying reason behind any irregular betting behaviour.
 

Latest revision as of 00:01, 8 September 2016