GRADUATION RESEARCH CHANTAL BLOM - PART 2

It has been a while since I told you about the Data Science project that I am working on together with BDC and the Dutch Handball Association (NHV).

In the meantime, we are already halfway through the project in terms of time and it has become a lot clearer which direction we are going in terms of data analysis. In this post I will explain what the idea is and where we are now.

At the NHV, data is collected on handball talents from different teams.
This is data from measurements such as high jumping, throwing from different positions, a sprint test, etc.
The measurement results of the talents are now structured.

The idea now is to give scouts and trainers an opportunity to compare talents.
For example, it can be useful for trainers to see where similar talents differ
and what a talent could train extra for.
We compare talents by determining the distance between talents in the feature space.
We then look at the k nearest talents.

There are now two parameters that can make a comparison better or worse; the number of talents we look at and the measurement results we include in the comparison.
To determine the best combination of these parameters, we use k-Nearest Neighbor regression.
We use some of the data to try out different combinations.

The video below explains how the best value of k can be determined
using k-Nearest Neighbor regression.

The idea is that we use the algorithm to estimate the value for each measurement of each talent and
determine the difference between the estimated values and the actual values.
We do this for different combinations of k and properties.

The model, the best value for k and the best combination of properties, can be used in various ways in an application to compare talents.

I will share more about this in a future article.

Chantal Blom

Business Data Challengers