5-min presentation of EW-Shopp. EW-Shopp is an industry-driven H2020 project where AI is used to make data enrichment easier and predict the effect of weather and events in different business domains such as eCommerce, Retail, CRM, IoT, Digital Marketing

1. EW-Shopp: Supporting Event and Weather-based
Data Analytics and Marketing along the Shopper Journey
Matteo Palmonari, Michele Ciavotta, Flavio De Paoli, Vincenzo Cutrona - University of Milan-Bicocca
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732003.
H2020-ICT-2016-2017- Topic: ICT-14-2016-2017
Starts on Jan 1st 2017, ends on Dec 31st 2019; NOW: M27
Total cost ≈ 3.6M€ - Total funding ≈ 2.9M€

2. CONSUMER JOURNEY ANALYTICS
LOCATION INTELLIGENCE
DIGITAL MARKETING CAMPAIGN
OPTIMIZATION
Business Cases & Pilots
• Weather-aware widget: enrichment of purchase information for
customers of eCommerce platforms
• Category and marketing optimisation software ecosystem with
weather and event-based sales predictions
• API and decision-making system for resource allocation in CRM
contact centers with weather and event-based predictions
• Scout+: dashboard for location intelligence based on weather and
seasonality trends
• Weather-aware scheduler for digital marketing campaigns in
search engine platforms
Consortium: 7 companies + 3 research organizations

3. DIGITAL MARKETING CAMPAIGN
OPTIMIZATION
Business Cases & Pilots: Example
• Weather-aware scheduler for digital marketing campaigns in
search engine platforms
Consortium: 7 companies + 3 research organizations
opp 2017 GA number: 732590 H2020-ICT-2016-2017/H2020-ICT-2016-1
Figure 11: Example of column generation in DataGraft by data addition
e the datasets are completed, QMiner will develop the analytics required in each case, from the
e variety of algorithms included in libraries like Spark MLlib.
conclude, a particular example, during the last HandBall WorldChampionship that took place in
many, we monitored the correlation between the German Team matches and the on-line digital
mpaigns indicators under the “SportFitness” category.
Figure 12: Correlation between German national handball team matches and online digital
indicators in the "SportFitness" category.
300K campaigns in 74 different
countries bidding over 2B keywords,
daily

4. Corporate Data
Weather
Data
Weather
APIs
Event
Data
Events
APIs
VISUALIZATION
Knowage
ANALYTICS
QMiner
DATA INTEGRATION LAYER
Grafterizer + ASIA
enrichment
shared systems
of identifiers
Aprroach Overview and Technologies
CONSUMER JOURNEY ANALYTICS
SEMANTIC PRODUCT DATA
LOCATION INTELLIGENCE
DIGITAL MARKETING CAMPAIGN
OPTIMIZATION

5. 5
Event-based predictive analytics combining
structured and unstructured data
• Data harmonization
• Volume and variety of data (300K campaigns in 74
different countries bidding over 2B keywords, daily)
• Dealing with large-scale event data
AI-related challenges…
ASIA: automatic interpretation and annotation
of tables with human in the loop
• End-to-end semantic data transformation and
enrichment tool
• Layers of intelligent components (entity linking,
schema matching)
Weather and event-based predictive models
for Commerce, IoT, Digital Marketing, CRM
…and Contributions

6. Visit our data blog at www.ew-shopp.eu/data-blog !
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732003.
www.ew-shopp.eu
@EwShopp
EW-Shopp H2020 Project
Get in touch
with us at
Matteo Palmonari
palmonari@disco.unimib.it