Rise in Data Volumes and what this means for Sports Organisations (Blog 2)
5 May 2023 | Written by Andy Nutting
Blog 2 from our latest series by Information Governance Manager, Andy Nutting
In Andy’s latest blog series he takes a further look at what is causing this exponential rise in data within sporting organisations and what it is being used for.
Last time around I started to look at the rise in data volumes. At some point you need to manage all of this data, and I’ll look at this in the next article.
But first, what is causing this exponential rise in data? What’s it being used for? Well in the sports industry analytics is a big contributor.
Many sports organisations have embraced technologies that provide them with rich data using logarithms or AI to provide a competitive edge, or improvement in efficiencies, or predicting the future.
Here are some examples.
The use of wearable technologies in sports is helping to identify players with a higher risk of injury, allowing fitness staff to balance their overall exertion levels and enrol them in conditioning programmes if needed.
The use of Logarithmic Regression models via Binomial Distribution is commonly used to assess the probability of player injuries.
Use of multiple platforms and comprehensive data software allows analysts to obtain Neuromuscular data and store it in a data warehouse and this data can be tracked throughout the season to identify changes.
Numerous factors coalesce to create a player’s market value. They’re overall hype and brand name, level of performance, and consistency, all play an essential role.
When a team decides to make a sizeable financial investment in any player, they must have data available to justify their investment.
It’s no longer just about sending a scout to watch a player to make an assessment, reams of data are analysed often using machine learning tools, and more recently artificial intelligence, to plan about a player investment.
Indeed, using a data-driven approach, smaller teams are competing in the top leagues by just buying the right players. And whilst their fans won’t thank me for saying this, Brighton and Hove Albion are one such example.
Around 20 years ago they were a team rattling around the lowest divisions in the English game, in financial trouble and playing games in a converted running track.
A new owner in 2008 set about changing this and set about a plan to build a new stadium for the club and create a structure that saw them sustainably climb the divisions.
That sounds straight forward, but when you consider Brighton has always been seen as a club with potential, they are not a team with a storied past and have never won a major trophy or been seen as a traditional top-flight club.
However, they were one of the first clubs to harness the power of data to give themselves a competitive advantage. Using the wealth of information accumulated by their owner’s analytics company the club has reportedly been able to scout players more effectively.
Using a sustainable data-driven model Brighton’s place in the Premier League is not reliant on a boom-and-bust approach that many other clubs have tried, and to date, is proving successful. As I write this article Brighton is a team trying to qualify for European competition next season.
I mentioned scouts earlier, and these guys are far from redundant in this model. They are often compiling play-by-play data and running this via machine learning algorithms to make predictions.
Using text-based sports data analysis and predictive modelling, scouts can better determine whether a prospect would be a visible fit on the team’s existing system.
Sports teams are increasingly using analytical data and visualisation techniques such as heat maps to identify opponents’ tactics in previous games.
The data puts a team in a position to predict how the opposition might set themselves up for the match and how they prepare for different in-game situations.
Using trusted insights and data collected across the course of the season, teams can gauge their competition and tailor their strategy to neutralise their opponents.
Evaluating Ticket Churn
Whilst many sports organisations focus on marketing to increase their fan or membership base, customer retention is almost always cheaper than acquiring new ones.
Sports teams and clubs are now using Logistic Regression models to determine ticket churn. Paired T-tests can be used to determine how specific promotions and campaigns will impact ticketholders and overall customer engagement.
These new techniques are making it easier for sports organisations to predict the percentage of season ticket holders that aren’t likely to renew their membership for the following season.
It allows clubs to better predict their return of investment on how the team performs on the field, for example, poor on-field performances are likely to impact game attendance.
Predictive data modelling can be used to gauge impact.
Gate receipt revenue is a significant income stream for most sports clubs. Using historical data and performance correlation models, sports teams can better understand how a change in pricing will affect fan engagement and gate receipt revenue.
Too much data?
So, we can see that sports organisations are collecting more data and types of use this is being put towards.
It seems inevitable that more and more data will be collected but how can sports clubs better leverage the data they’re collecting?
A substantial chunk of data remains unleveraged, due to challenges in data management and security and if this is not overcome by the implementation of data management techniques, sports organisations run the risk of hoarding data without extracting real value from it.
A survey conducted in 2020 found that organisations collect only 56% of the data potentially available through their operations, and out of this 56%, only 57% of data was used, meaning 43% went largely unleveraged.
The survey also shed light on the dispersed nature of enterprise data and found that organisations stored data in a mix of internal data centres, third-party data centres, remote locations, and cloud repositories. This can make data management difficult given it can result in disparate management tools, separate workflows, a lack of unified security and privacy arrangements, and challenges related to moving data.
The key to improved utilisation of data is in having a data strategy. In my next article I’ll be taking a look at what one is, how to develop one and why this is important, particularly as you’re now collecting and storing more and more data.
If you’d like support managing your organisation’s data, our team can help.
You can keep up to date with Andy’s blogs on his LinkedIn profile.