The Data Analytics Blog

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

All Posts

We've Outranked 99.92% Of FIFA World Cup Predictions On Superbru

July 16, 2018 at 9:22 AM

After a FIFA World Cup full of upsets, the South African data scientists at Principa outranked 99.92% of people on popular sports predictor site, Superbru.

Principa’s football world cup score predictions are done using various predictive analytics methods. Each method’s predictions have been submitted on Superbru.com. The best-performing algorithm uses the Bayesian Inference method. The model has been automated to adopt a machine learning approach in that it reselects variable and parameters every time it is run, adapting to how the world cup is unfolding. Results of games from previous rounds inform predictions for the next round and the model is proving more accurate than 98.81% of other Superbru predictions at the end of the tournament.

The machine learning component can take it a step further, though, by also learning from match results within the current round and updating every day. This yields slightly different predictions to the ones the model makes at the start of a round, and Principa have also been adding these predictions to Superbru. Using the latest available data is proving a successful strategy, as it outperforms the other predictions by more than 1%, beating 99.92% of Superbru participants.

The predictions are available on their website: https://wonders.principa.co.za/principa-predicts-football-world-cup-2018

Principa have also created an overview of some of the more interesting insights discovered during the data preparations: https://wonders.principa.co.za/football-world-cup-2018-statistics

 *This blog was originally posted on 29 June, after the Group stages (99.96%), and was updated on 6 June to reflect achievement after the Round of 16 (99.98%) and again on 9 July after the Quarter-Finals (99.97%). After the Semi-Finals, it was updated again on the 12th of July (99.96%), with the current version updated on the 16th of July, after the Finals.

Latest Posts

My learnings on the effective use of automated self-service bots.

Organisations and individuals, need to adapt and change to the new ways of working to ensure that we survive this pandemic, and protect our sustainability for the future.

The time is NOW for model validation and adjustment.

One of the major premises used in credit scoring is that “the future is like the past”. It’s usually a rational assumption and gives us a reasonable platform on which to build scorecards whether they be application scorecards, behavioural scores, collection scores or financial models.  That is reasonable until something unprecedented comes along.  You can read about this black swan event in our previous two blogs here and here

10 ways the COVID-19 crisis will affect your credit models (PART 2)

This is the second of a 2-part blog. You can read the first blog here.