Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Wiraya RTCD - innovative outbound communication through the use of Artificial Intelligence

Reference number
Funding from Vinnova SEK 1 911 814
Project duration March 2017 - May 2018
Status Completed

Important results from the project

The purpose & goal of the project were to develop the first prototype of an innovative outbound communication platform that, with artificial intelligence, optimizes the conversion rates. The assessment is that the project has achieved its purpose and goal with the prototype that has been developed and tested in a production environment with communication done towards real end customers. Decisions about when and what to communicate are taken by models built by different types of machine learning algorithms and we have seen an increase in conversion in the tests we have conducted.

Expected long term effects

The direct effects of the project are that we have a good working framework to continue our development from. Further results of the project are that we have developed a machine learning platform with associated architecture for receiving, storing and processing data. From a customer perspective, we can offer the ability to receive data, conduct analysis, and build models that predict when and what we should communicate to increase the conversion. In our tests, we´ve seen an increase in conversion compared with previous manual methods.

Approach and implementation

The design and implementation of the project have worked very well and has given many new insights for future work. The project was divided into four different work packages: WP1 Algorithm Ideation, WP2 - System Architecture, WP3 Develop Demonstrator, WP4 Verification of Solution. During the project, we redistributed time from WP3 to WP1 because we underestimated the complexity of WP1.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 25 November 2019

Reference number 2017-00520

Page statistics