Powered by

14.Weighted Parameters

Weighted-parameters-Algorithmic-Affordance

Weighted Parameters

Tuning algoritmic parameters

14. Weighted Parameters

Recommender systems typically base controls on a certain parameter sets. Users may be allowed to add weights to different parameters to adjust the recommendation space they get.

What can designers do with this pattern?

Example of peer pickers

Examples?

Fastcase 7

Input or output?

Input

How do users control the algorithm?

Parameter adjustments using sliders and drag and drop options have been explored.

How do users understand the control?

Controls may be interpreted as a way to change the scope and bias in recommendations.

Some examples of use

0
Weighted Parameters 001

Weighted Parameters 001

admin

0
Weighted Parameters-001B-Algorithmic Affordance

admin

0
Weighted Parameters 001

683Weighted Parameters

admin

0
Weighted Parameters-001B-Algorithmic Affordance

684Weighted Parameters

admin

Relevant theories

Please let us know if you have a related reference with the scientific research.

Comments & Talks

React on this algoritmic affordance and get in touch with the publisher over this algoritmic affordance Koen van Turnhout.

Add
Comment

Related Patterns

Related algoritmic affordance pattern in this library are listed below.

Reset-Algorithmic-Affordance

Reset

Tuning algoritmic parameters