Optimise the range of ads in the hotel and restaurant industry

Challenge:

Choosing an ad to show customers is a critical part of marketing in the online tourism sector. It is necessary to choose one that attracts consumers, but also ends in a potential sale. Analysing user search data must allow the probability and profitability of a specific ad to be defined and estimated.

Solution:

GCD@UB and an online travel company collaborated on the design of a tool to estimate the click-through rate of ads in the hotel and restaurant industry. The algorithms, which were developed based on regression models, have the capacity to process millions of attributes and allow decisions to be made in real time regarding the best ads to show at any given moment.

Image

Impact:

Making decisions about which ads to show customers should aim to increase the effectiveness of marketing so that it is relevant to the consumer and, in turn, profitable for the company.

Related Articles

Application of deep learning techniques to detect semantic changes in aerial images.

cat.
14.01.2019

We have won a new competition with the Cartographic and Geological Institute of Catalonia, to apply deep learning techniques in the detection of changes in the network of infrastructures and constructions in the territory with the aim of automating the process of elaboration of the Topographic map of Catalonia.


Development of an IA tool for the detection of pathologies in endoscopic images.

cat.
14.01.2019

Joint development with Vall Hebron Hospital of a scalable medical diagnosis solution based on artificial intelligence tools for CorporateHealth International ApS.

 


Development of a leather classification system by means of artificial vision

cat.
11.10.2018

DataScience@UB designs and prototype a machine that includes an intelligent vision system based on semantic segmentation through convolutional neural networks to automate the classification of leather.