In our exclusive roundtable discussion, we spoke with some of the most innovative experts in sports analytics. Here we learn about their career experience and cutting-edge technical expertise.

Boosting the Accuracy of Your Analysis by Training Your Algorithms

When it comes to boosting the accuracy of your analysis by training your algorithms, the first step is integrating data into the algorithm itself. Lorenzo Malanga, head of data science at sports betting and data company Mercurius explains their process.

“What we do is find patterns in historical data in order to gain an edge over the betting markets,” said Malanga. “Hence, we make use of Wyscout data in our predictive algorithms to measure the skills of every team at every point in time and assess how this translates in a good or bad performance with respect to expectations. Without it, it would be harder to spot market biases and misjudgments.”

Better accuracy of data in this field of course will relate to more profitable outcomes and will also allow an advantage over competing entities. But with predictions comes risk. Paolo Cinta, CEO and co-founder of player performance evaluation company PlayeRank shared his thoughts on the link between human and machine skills.

To learn more Download Data Samples and/or book a time with one of our experts.

“The key is explanation as machine learning techniques are a sort of meta-algorithm: they use data to automatically generate new algorithms, capable of performing a task they have been trained to,” said Cintia. “Such new algorithms tend to be black-boxes: they work, they produce predictions, but the underlying motivations leading to that prediction are not completely transparent. This process of knowledge extraction and explanation enforces a co-operation between human and machine skills, heading towards a continuous refinement for both.”

Having the most up-to-date and accurate data is the best way to keep accuracy of predictions high. But what about the value of using data from past seasons? “Malanga says, the more past data, the better.”

We extensively make use of past seasons data to train our models and to backtest trading strategies,” said Malanga. “To stress it further, by having more data, we can make more experiments without increasing the risk of ‘overfitting’, i.e. the common curse of ‘remembering’ past data rather than ‘learning’ from it. There is also a clear alignment between technical and commercial values: the deeper the historical set on which we tuned our algorithms, the more credible and robust our strategies become to our clients' eyes.”

To learn more Download Data Samples and/or book a time with one of our experts.

Extensive Geographical Data Coverage Enables You to Not Have Blindspots

Cintia described to us that for companies that plan to scale globally, extensive geographical data is key, especially in terms of scouting.

“For performance monitoring and scouting, having a wide geographical coverage is fundamental,” said Cintia. “We discover new players since the beginning of their careers, and this is very valuable for clubs. Data has to be machine readable - it's not obvious, unfortunately - and should cover all the aspects of player and club performances: from matches to training load, financial aspects and media coverage.”

With his next point, Cintia explained that with international players from all continents and world leagues becoming more popular in football, it is now extremely important to have data available from leagues across the globe.

There is also a clear alignment between technical and commercial values: the deeper the historical set on which we tuned our algorithms, the more credible and robust our strategies become to our clients' eyes. Lorenzo Malanga - Head of Data Science at Mercurius.

“Historical data allows us to find new players, and to extend the possibility of performance analysis and comparison,” said Cintia. “As an instance, we found that the player with most goals scored in a single game is a Chinese female player. Now we know that it's possible to score 9 goals in a single match, it was in a game scored 16-0 to China over Turkmenistan. This could seem kind of fun, but we can do the same for plenty of similar metrics—it's really valuable.”

Extensive geographical data is also very useful in terms of influencing algorithms and comparing data between different leagues. 

“We tend to model each league and country as a universe per-se,” said Malanga. “Of course, some analysis may benefit by grouping together different leagues’ data. But in general, an extensive geographical data coverage would simply mean a wider set of leagues for which we train predictive algorithms.”

To learn more Download Data Samples and/or book a time with one of our experts.

It Takes Large Data Sets to Get Ahead of Your Competition

Wyscout data can be combined with multiple other data providers to provide added statistical benefits. Meza explained the value of working with multiple data providers from the perspective of Twenty3 Sport.

“For us it's not about ‘combining’ the data to improve algorithms or models - in fact we keep data from data providers in completely different silos,” said Meza. “The reason we work with multiple data providers is that we want to provide technology to make use of the data and extract insight from it for clients, and different clients have licenses with different data providers, therefore we must tender for multiple data providers ourselves to increase our potential pool of customers. Also, we endeavor to set up our tools in a way where the details of the data are still available to the end users through our tools - for example, Wyscouts "tags" on event data can be used in our tools, to also empower the provider to innovate in their data, and for that to make its way to the end users.”

In terms of taking advantage of multiple data providers to get ahead of competitors, Cinta said he “would say it allows us to image and develop better products”, while Malanga drew the conclusion that “it allows us to mitigate the risk of corrupted data, plus it means we are able to capture a higher level of detail, as different companies have different data compiling procedures”. 

Historical data allows us to find new players, and to extend the possibility of performance analysis and comparison. Paolo Cinta - CEO and Co-Founder of PlayeRank.

Increased Interest in Emerging Markets is on the Rise

In certain countries, football is flourishing where it isn’t traditionally the primary national sport—and the level of play is rising along with its revenue. A key example is in Japan where the J1 League and DAZN have closed an exclusive deal for the next 10 years. When asked how important it is to enter these emerging markets, Meza said “It’s definitely important as if coverage of J1 League opens up commercial opportunities to our clients, (for example content providers like DAZN), then us having those leagues within our coverage means we can tap into those customers and share the revenue.”

Cintia also sees big potential for commercial benefit in emerging markets, stating “We actually attracted the interest of some players from the asian continent, and there is no doubt that many countries are fascinated by football, aiming at developing their clubs. We could be an opportunity for them, providing tools to speed up the process of decreasing the gap. Both market and sport competitions would become harder, but the whole sector would gain from this, and consequently grow and expand." 

Meza concluded the topic of emerging markets value by saying, “Coverage and scale are good friends of data-driven processes - there's no doubt about that. Tapping into that is crucial in providing value to customers, and therefore finding revenue opportunities.”

To learn more Download Data Samples and/or book a time with one of our experts.