The challenge of integrating new data and collection techniques with old data

The challenge of integrating new data and collection techniques with old data ...

Andrew Brust and Tony Baer have been invited as regular contributors to VentureBeat in order to further strengthen our commitment to providing industry-leading data technology. Watch for their articles in the.

The use of new technologies or systems can be costly or omnipresent in order to avoid businesses in the corporate world. There are often times when new technologies or systems become too expensive or ubiquitous to not integrate in the business world. Those organizations tend not to last long.

There are instances of development that try and fail to merge the old with the new, while others make it happen. This is seen on full display in sports, where organizations are challenged to integrate legacy data with new collection technologies and data sets. What sets the success stories apart?

When faced with huge amounts of new data due to advances in and, a sports organization should first acknowledge that it's a good problem to have. With advances like, for example (a laser-based movement tracking system), that is focused on increasing accuracy, depth of information, and seamlessness of data collection, performance evaluationators now have access to an enormous, untapped trove of data that can be used to better inform their decisions. The question then becomes: How does a club manage that influx of new data?

First, offer patience. Consider that organizations and their data teams have used the same approaches and assumptions for years. Old habits die hard, and because advanced analytics can be applied to everything from game strategy to the optimal soda served at the stadium concession stands, an organization will need a cross-the-board buy-in. That takes time.

The biggest challenge is integrating the historic information of an organization with other new techniques. Today's data looks very different than previously, and in some cases, the kinds of measurements don't align with. What's the purpose of this study? Start here:

  • Run translation exercises. Set aside a transitional period during which a detailed analysis of all data and methods both modern and historic is conducted.
  • Amass a statistically significant amount of data. Avoid any statistical noise or false positives a too-small sample size could yield. Youll want to get this right the first time.
  • Be aware of biases. Certain predilections could occur in the calibration of the system. Identifying and correcting them are important to avoid building bias into your baselines and future calculations.
  • Account for differences in data collection methods. Different sports venues use a variety of tracking technology, some of which have inherent limitations that influence the data collected.
  • Know that some translations can be probabilistic in nature. Measure to a constant: in other words, player X runs at a speed of Y, so the new measurement output should be equal to Y.
  • Integrating old and new data can be laborious. Making sure that old data sets arent lost while embracing the insights new data unlocks can be costly and time-consuming. But its important to remember after the exercise that an organization will be better positioned to make personnel decisions.

The key to success in integrating old and new technologies, methodologies, and information is to take a deep, thorough dive into the data. Most clubs need to know that raw historical data to be easily understood by new user profiles down to make it viable, which takes significant time and may further increase its value in the process.

Different technologies or approaches may create a schism between data sets tracking similar or identical movements. For example, data collected from wearables attached to a player's boot may not easily integrate with data collected that was classified with a laser-based lidar.

Because of missing data points, wearable technologies are limiting where and how often those measurements can be performed. However, there may be gaps in the tech's feedback. Data smoothing can't assist this information.

Upgrading to new technologies is often beneficial. Take lidar, which is more accurate from the perspective of a player than previously. The difficulty of data integration is the only significant feature to adopting lidar in a club's player evaluation department. And with the right plan, even that obstacle can be resolved.

Raf Keustermans is the CEO of.

Welcome to VentureBeat's VentureBeat community!

Experts, including technical individuals who are doing data work, can share data-related insights and innovation.

Join DataDecisionMakers for an upgrade to cutting-edge ideas and up-to-date information, and practices, as well as the future of data and data technology.

You might even consider your own!

You may also like: