How to ensure data privacy? We pay particular attention to the protection of your horses’ data. Confidentiality is a central issue in data collection, sensitive in our industry, which is why it is at the center of our concerns.

Thus, when using the EQUIMETRE sensor, Arioneo collects data and is committed to respecting the strict confidentiality of your personal and equestrian data privacy.

Data privacy of equestrian data generated with EQUIMETRE

Within the framework of the collaboration between a trainer or veterinarian and Arioneo, equestrian data are collected and stored in a confidential and secure database. These data constitute a database composed of elements regularly measured by the EQUIMETRE sensor: at each training session, the sensor measures more than a hundred parameters which are stored in our database.

At Arioneo, this database is a powerful development tool for us, with the sole aim of constantly improving our sensor, our understanding of our users needs and our service. This access to our database also allows us to develop and refine our calculation algorithms in the EQUIMETRE platform.

Data coaching

During the data coaching sessions, we analyze with you the training data of the horses of your choice. These data are analyzed by a data analyst of our team, who is contractually bound to respect the strict confidentiality of these data. Moreover, an additional and co-written confidentiality agreement with you can be signed upon request.

In case you do not wish to share your training data with our data analyst, the data analyst will not have access to it, but will not be able to analyze it with you.

Improving our products with data

The EQUIMETRE sensor is a constantly improving sensor, and the data we collect and save allows us to improve it at any time. In this process of data use, the data is absolutely anonymous.

In particular, we use a technology called machine learning, which is an artificial intelligence technology that allows computers to autonomously develop new algorithms based on very large databases.

For example, machine learning enabled us to establish the recovery levels which are now used on the EQUIMETRE platform. To establish them, our team gathered all the data about the recovery of horses during monitored training sessions. Using this process, we were able to establish precise recovery levels and be able to qualify the recovery of each of the horses monitored in the analytics section.

Machine learning was also used to enable the EQUIMETRE sensor to detect the gait of the horses during training. By using a database of racehorse gaits, the machine learned to detect the different gaits of a horse (walk, trot, canter, etc.). This has also led to the creation of a value prediction model that simply allows the removal of abnormal values that can be introduced among all the data monitored in a training session. By calculating the different gait models of racehorses, we can easily eliminate data such as stride frequency data, for example, which are not related to the horse’s gait at the moment.