Data Fusion 2021

The first international conference devoted to the synergy of Data Fusion data took place in March 30 - 31, 2021 in the Skolkovo Innovation Center
96
SPEAKERS
50+
SPEAKERS
25
SESSIONS

DATA FUSION 2021 PROGRAM

Opening speech. Vadim Kulik, Deputy president - chairman of the board, VTB Bank
Session «Data Fusion and work with customers» featuring Gartner, Tele2, Multicarta, VTB Bank, Russian Post
Discussion «Legal issues in Data Fusion concept»
Session «Unified Data Fusion»
Session «The future of data science and machine learning: critical trends you can’t ignore»
Discussion «Artificial Intelligence factory»
Discussion «Artificial Intelligence, data and government»
Science notes «Compositional AI: Fusion of AI/ML Services»
Science notes «Prospects to ensemble neural connections»
Session «Machines see everything. Computer vision and Data Fusion»
Science notes «ML-renaissance of time-series forecasting»
Discussion «NLP» featuring Skoltech, DeepPavlov, VTB Bank, Huawei, Skoltech, Rostelecom
Science notes «Artificial Intelligence vs fakes and post-truth politics»
Session «A system approach to teaching Data Science»
Science notes «Bipartite graph of science and industry»
Session «Data classification and recommendation systems»
Session «Time series in economy»
Analysis of Data Fusion finalists’ solutions
Session «ML-Renaissance of timeseries forecasting»
Session «Graph analytics»
Data Fusion 2021 Videos

DATA FUSION 2021 CONTEST

Data Fusion Contest is a data science competition with a dataset of unprecedented volume and structure, formed from 7 000 000 simulated receipts. Participants were tasked with developing solutions for digitizing customers' experience.
1000 PARTICIPANTS
18 COUNTRIES
50 CITIES
8 WINNERS
2 000 000 ₽ PRIZE FUND
Nominations and Winners
Task №1
Prize
Winner
GOODSIFICATION
1st place
500 000 ₽
flow
2nd place
250 000 ₽
hype
3rd place
150 000 ₽
keks
For the best public decision
50 000 ₽
exotol
For the speed of the solution
50 000 ₽
Niw
Task №2
Prize
Winner
BRANDEFINE
1st place
500 000 ₽
GIA
2nd place
250 000 ₽
Niw
3rd place
150 000 ₽
Artem Voronov
For the best public decision
50 000 ₽
InfusionTeam
For the speed of the solution
50 000 ₽
Artem Voronov

Tasks

Task №1
GOODSIFICATION
Classification of data from receipts
Classifying data from modeled receipts, creating a goods classification algorithm on really big data. Creating a unique classifier for a wide range of customer bank services that has become one of the key parts of solving tasks on enrichment a customer’s portrait, personifying communication with him, improving customer journey.
Metric
Weighted F1score
Solution format
Code in a docker container
Task №2
BRANDEFINE
Product brand definition
Defining a brand of the item by its name with the help of current NLP-methods. Teaching a brand highlighting model to improve lives of millions of people through the continued development of the bank's customer service and partner ecosystem. Saving customers' time and providing only useful information for them.
Metric
Accuracy
Solution format
Code in a docker container