The Problem

Despite recent advances in artificial intelligence and machine learning the industry is still struggling to find answers to the 6 core problems of sports data.

Supply Problems



Sports organisations are driven to pursue any incremental advantage over their competitors, that something extra to improve performance and gain an edge.

Data can be used to advance these fine margins, the incremental gains.

But there is no standard, no absolute defined measure of what data is actually needed to achieve the gain. There is no validated data specification for any given sport. It is left to individual coaches and analysis’s to mine the relevant gold in a mass of numbers.



Sports Data is commonly gathered manually by humans; as a result, the quality of the data is often inaccurate and inconsistent.

Inaccurate data is a basis for incorrect predictions. Organisation are dependent on accurate data, they are basing entire strategies on it, from player selection to game tactics. In todays modern sport environment, the phrase ‘junk in, junk out’ is more relevant then ever.



Organisation want certainty. Certainly, their product will sell, their team will win, their new recruit will perform. In order to gain certainty organisations look to forecasting, modelling, and predictions. In order to get great predictions or great forecasting, you need massive amounts of data.

Currently the sample size of historical sports data is simply too narrow for organisations to make accurate forecasts and worthwhile insights.

Efficiency Problems



The context, design, and delivery of sports data generally don’t suit the customers’ workflow.

Teams must sift through reams of numbers to find the relevant story to their needs. Analysts have to analyse and decipher data to put it to use.



Speed is a huge driver and critical aspect of any deliverable in sport.

Human-led gathering techniques are just not fast and accurate enough and subject to human error.



Harvesting masses amount of data without a clear understanding of what data is needed lacks efficiency and is costly.

Human-led gathering techniques are limited to human ability, talent, training, and experience and are costly.

How can we help?

TEN14 are solving these problems using artificial intelligence and machine learning to create large volumes of accurate and validated sports data.