The Data Analytics Blog

Our news and views relating to Data Analytics, Big Data, Machine Learning, and the world of Credit.

All Posts

Using Predictive Analytics To Beat The Bookies

September 22, 2015 at 4:49 PM

Hand holding a crystal ball predicting the result of the Rugby World Cup using Machine Learning

It’s Man vs. Machine at Principa HQ as our data scientists apply predictive analytics and machine learning to predict the winners and spread of each match during the Rugby World Cup. 

We signed up two internal teams of data scientists onto sports prediction site SuperBru.com as an exercise to put theory into play in this year’s Rugby World Cup. By applying the same principles used to predict customer behaviour for our financial services and retail clients, our two teams are vying against each other to develop algorithms and predictive models that can predict the outcome of the matches with the highest accuracy.

The purpose of the exercise is to see how well predictive analytics techniques used successfully in other areas can outperform the best human made predictions within the context of sport on SuperBru.com.   

Analysing data from 6,000 rugby matches

Our two teams – Nero and Trojan - are looking at a wide range of data to predict as accurately as possible the win-lose outcome of each match and the margin between the two teams. The teams are considering data and information, such as recent performance, bookie odds, each team’s current world rankings, previous number of tries and even the value of individual players from a fantasy league.

They've looked at data from over 6,000 matches played by 99 teams going back 20 years to identify patterns that are highly probable to repeat in future. However, due to the many human variables in a match – such as injuries, penalties, referee calls, last-minute player decisions and even health - we may not be able to predict the exact scores, but with each match we will be able to provide an increasingly high probability of our predicted outcome.

As the objective of machine learning is to develop computer programs that can teach themselves to grow and change when exposed to new data, the two teams will be adjusting their algorithms with the results of each Rugby World Cup match to improve the accuracy of each prediction generated.

Our guys are learning from every match and adjust their models to account for new variables, including the teams’ coaches and their experience as was the case in the upset match between South Africa and Japan. Hopefully, we can get closer to predicting upsets as we enter new information such as this.  

Some interesting insights gleaned from 20 years of rugby data

Some of the more interesting statistics and patterns they've discovered from analysing over 6,000 matches played by 99 teams since 1995 are:

  1. New Zealand have won 84% of the matches they have played compared to 66% wins by Australia, 62% wins by South Africa, and 61% by England;
  2. New Zealand scores an average of 36.9 points in a match compared to 28.9 by Australia, 28.5 by England and 28.4 by South Africa; and
  3. On average about 20% of all matches were upsets where a higher ranking team was defeated by a lower ranking team.

Check for the latest predictions and new rugby insights!

We've made a page available here with an overview of all the insights they have derived from the past 20 years of rugby.

We will also be posting each teams’ data-driven predictions before every match as well as via Twitter (@PrincipaD) and Facebook - so follow us, if you'd like to check our predictions before every match! You can check out our last set of predictions here.

It will be interesting to see how accurate our algorithms and models are in predicting the outcomes of the matches. In reality, relying on data insights without proper interpretation by subject-matter experts can lead to sub-optimal if not disastrous results. So, we encourage all you rugby fans to use our data-driven predictions as a starting point upon which to apply experience and your own knowledge - and a dash of “gut” feeling – to make your own predictions for each match! 

predictive analytics guide

Julian Diaz
Julian Diaz
Julian Diaz was Head of Marketing for Principa until 2017, after which he became Head of Marketing for Honeybee CRM. American born and raised, Julian has worked in the IT industry for over 20 years. Having begun his career at a major software company in Germany, Julian made the move to South Africa in 1998 when he joined Dimension Data and later MWEB (leading South African ISP). Since then, Julian has helped launch various South African technology brands into international markets, including Principa.

Latest Posts

[Slideshare] How To Make Your Business Data Work For You

Common barriers to success: Skills shortage: data scientists are in high demand and in low supply. Companies lack the skills to develop advanced data analytics or machine learning applications. Cost: recruiting and building up or training a team, as well as infrastructure costs are immense. Inefficiency and low ROI on: acquisition campaigns; re-activation and retention campaigns; outbound sales calls and debt collection. Resulting in: No or ineffective use of data. High cost to get insights from data. Low returns from campaigns. What’s the alternative? Machine Learning as a Service (MLaaS): removes infrastructure skills and requirements for machine learning, allowing you to begin benefiting from machine learning quickly with little investment. Subscription based pricing, allowing you to benefit using machine learning while minimising your set-up costs and seeing returns sooner. Answers as a Service: Use historic data and machine learning to allow answers to increase in accuracy with time. MLaaS with predictive models pre-developed to answers specific questions: Genius Call Connect: What is the best time and number to call customers? Genius Customer Growth: Which customers are most likely to respond to cross-sell? Genius Re-activation: Which dormant customers are worth re-activating? Genius Customer Retention: Which customers are most likely to churn? Genius Leads: Which contacts are likely to respond to my campaign? Genius Risk Classifier: Which debtors are most likely to pay or roll? Benefits of Genius: Quick and cost-effective ability to leverage machine learning: Minimal set-up time Minimal involvement from IT Subscription based service Looking to make your data work for your business? Read more on Genius to see how it can help your business succeed. 

5 Must-Join Facebook Pages For Data Science, Machine Learning And Artificial Intelligence In 2019

While LinkedIn has traditionally been thought of as the business or work focussed social platform, Facebook has been making headway into gaining market share in the space as well. With company pages and groups, Facebook is catering to every interest and aspiration that people might have – and combining that with their social interactions and news sources. Facebook aims to give users a one-stop-shop experience, and it’s very good at doing it.

Our 2018 Customer Acquisition And Engagement Blog Roundup

Our final roundup this year covers two of our main topics: customer acquisition and customer engagement. We’ve not covered these topics in depth this year, and so decided to combine these two to provide a roundup of the best of both.