The goal of this pilot solution is to develop data driven services to improve the impact of Digital Marketing Campaigns establishing the best moment to launch the campaign and predict its performance as a function of the weather and external events.
Key objetives of the pilot are focused on the enrichment of tha data value chain by:
- Integrating external data (weather and events) with marketing performance indicators
- Aggregate the data sets according to the expected impact and campaign management strategy
- Generate temporal models about keywords/categories behaviour
- Implement 4 different services supporting a more efficient digital marketing campaign management
JOT expects to improve all the most relevant marketing indicators in digital marketing such as: impressions, clicks and CTR. All these are related with both the quality of the campaign management and the traffic generated for client’s site. High quality traffic will generate some kind of conversion in the landing page like sale, lead or expression of interest.
This service will mostly impact JOT’s campaigns, generating high qualified traffic to our clients sites. In the future, this service can be used to boost the impact and performance of digital marketing campaigns of SMEs, where the keyword list describing their business and service are shorter and the influence of the nearby conditions are more critical.
So far, it has been implemented, at low scale, the service enabling the prediction of the most adequate date to launch a campaign depending on the weather forecast at region level.
The first pilot showed that the EW-SHOPP approach and data flow can be implemented and deploy for campaign management. Although there is some work to do in terms of scalability, it has been posible to integrate weather data and modelized the keywork behavoiur. So, by downloading one week weather forecast. aggregated at region level and based on a keywork list (for the next campaigns) it is posible to predict when the campaings have to be activated.
Next actions will be focused on:
- Integration of external events
- Modify the keyword modelling approach to improve the scalability of the service
RESEARCH & INNOVATION DOMAIN: Data integration, data aggregation, modelling, predicion, user interface and simple visualization
TOOLS INVOLVED: Google API, ArangoDB, Grafetizer, R-coded models and algorithms, RStudio
CONTACT PERSON: Fernando Perales firstname.lastname@example.org