The 2019 European DatSci & AI  Awards

Finalist Projects

Each year the DatSci Awards has gone from strength to strength, with the 2019 Awards being the best yet. More than 2.5 million people from the Data Science, AI and Analytics community across Europe were reached by our digital campaigns this year. This helped to attract more applications than ever with individuals and teams in 13 countries entering into the competition to get recognised in this growing industry.

Learn more about this year’s winners and finalists by checking out their projects below.

AWARD FOR BEST DATA
SCIENCE STUDENT OF THE YEAR
Best use of Data Science/AI for Health & Wellbeing
Best use of Data Science/AI
for Health & Wellbeing
Best technical advance in the field of Data Science/AI from a research organisation either in academia or industry
Best technical advance in the field of Data Science/AI
Datsci Innovation
DATA SCIENCE TECHNOLOGY INNOVATION
OF THE YEAR
Datsci Social Impact
BEST USE OF DATA TO ACHIEVE
SOCIAL IMPACT
Best use of Data Science/AI for Industry 4.0
Best use of Data Science/AI
for Industry 4.0
Best use of Data Science/AI for Customer Experience
Best use of Data Science/AI
for Customer Experience
Best use of Data Science in SME/Start Up
Best use of Data Science
in SME/Start Up
Best Application of AI
Best Application of AI
of the Year
Data Scientist
of the Year

BEST DATA SCIENCE STUDENT OF THE YEAR

Our ‘Data Science Student of the Year’ award highlights data science research projects conducted by students, as well as the relevance and impact of their research work. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: RORY BOYLE
TRINITY COLLEGE DUBLIN

This project developed an accurate and interpretable model of brain-predicted age differences (brainPAD) using open-access MRI data. The model was validated on external datasets, containing rich cognitive data. The brainPAD cognitive function relationship was assessed in each external dataset in order to investigate its utility for objective measurement of cognitive function, which is critical in order to identify individuals at risk of significant cognitive decline.

*Click below to learn more about Rory’s project.

Finalist: Gaurav Pahuja
SSE Airtricity

Data Optimisation Network is an end to end application which connects multiple databases together to create a 360 degree view for the business on a same geospatial index through using machine intelligence and data science techniques. DON will seek to accelerate the growth of the business. It will work as a proactive and reactive solution platform which will enhance business strategic decisions.

*Click below to learn more about Gaurav’s project.

Finalist: Amal Saadallah
Tu Dortmund

Matching supply with demand in dynamic environments is one of the biggest issues faced by many industries such as the taxi industry. BRIGHT: a drift-aware supervised learning framework is proposed to predict short-term horizon taxi demand through a creative ensemble of time series analysis methods that is able to handle distinct types of changes/concept drifts to cope with the dynamic behaviour of urban mobility patterns.

*Click below to learn more about Amal’s project.

Finalist: Andrew Kenny
University of Limerick

Opinion polls are becoming less reliable in predicting political views, as seen in high-profile cases such as the 2016 US Presidential election and Brexit. This research proposes that the application of machine learning to social media can provide a viable alternative, while also addressing underlying issues found in traditional methods such as social desirability bias and confirmation bias.

*Click below to learn more about Andrew’s project.

Finalist: Dixon Vimalajeewa
Waterford Institute of Technology

The social network analysis (SNA) is now commonly used to characterise the behavioural dynamics of social groups. The increasing complexity of SNA data necessitates the investigation of novel strategies to transform such data into useful metrics, which can subsequently be used to support day-to-day decision making. A novel matrix, Animal importance is derived based on GPS mobility data to explore and identify atypical social behaviours in cows in smart dairy farming.

*Click below to learn more about Dixon’s project.

Finalist: Suad Al Darra
National Univeristy of Ireland, Galway

Are refugees a threat? How do news articles describe refugees and migrants? This work highlights the issue of xenophobia against displaced people by applying the latest data science methodologies over open-source news datasets to train a classifier that could automatically detect xenophobia language, and also to find a better visual way to tell the narrative about refugees.

*Click below to learn more about Suad’s project.

Best use of Data Science/AI for Health & Wellbeing

BEST USE OF DATA SCIENCE/AI
FOR HEALTH & WELLBEING

Our ‘Best of use of Data Science/AI for Health & Wellbeing’ award showcases how they have applied Data Science/AI as part of a live implementation to progress individual and community health and wellbeing. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: AXIAL3D
Using AI to 3D Print models of body parts to improve surgical intervention

By transforming a patient’s MRI/CT scan into a 3D-printed object, surgeons and patients can make better treatment decisions. The solution developed by axial3D spearheads a new area of medical-imaging segmentation, focusing not just on the detection and extraction of specific anatomical regions from medical scans but doing it in such a way that it is then 3D-printable. Enhancing existing practices and improving patient outc omes.

*Click below to learn more about axial3D’s project.

Finalist: Environmental Protection Agency Ireland
Tracking Change in Waste Water Treatment Plant Performance

Discharges from waste water treatment plants are one of the main treats to our freshwater environment in Ireland. The performance of each plant is tracked using simple statistical metrics like t-tests and sign-tests. The metrics are summarised in a dashboard that shows (at-a-glance) how each plant is performing, and its impact on the surrounding environment.

*Click below to learn more about Environmental Protection Agency Ireland’s project.

Finalist: DCU INSIGHT CENTRE FOR DATA ANALYTICS
GaitKeeper

Gait is an excellent predictor of the onset of many physical and neurological conditions. It is often referred to as the 6th vital sign. However, there are no easy to use systems that provide quantitative results at low cost. GaitKeeper provides the world’s first gait analysis as a service – making it easy for clinicians to create spatial and temporal gait analyses from videos recorded using the GaitKeeper mobile application.

*Click below to learn more about this project.

Finalist: IBM Research
InterACT: A cloud-based platform for multimorbidity management

InterACT is a platform for multimorbidity management that hosts the HWProfile. A tool for risk exploration it works to build a holistic representation of the individual over several dimensions including vitals, symptoms, conditions, demographics and behaviours. InterACT and the HWProfile have been tested in a pilot trial of 120 patients over 65 with multiple chronic conditions in Ireland, Belgium and Italy.

*Click below to learn more about this project.

Finalist: IBM Innovation Exchange
The Social Campaign Manager

The IBM Social Campaign Manager (SCM) is a solution for policy makers that are responsible for health care and wellbeing globally. The SCM is an end to end solution for capturing  the voice of the public and sentiment on current and future policy reform. Conversations with the public are defined, launched and analysed by the SCM using AI and social media.

*Click below to learn more about this project.

BEST TECHNICAL ADVANCE IN THE FIELD OF DATA SCIENCE / AI FROM A RESEARCH ORGANISATION

Our ‘Best Technical Advance in the field of Data Science/AI from a Research Organisation’ award recognises individuals or teams working together on the technical advance in the research field of Data Science/AI by the nominee. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: Accenture Labs
AmpliGraph

AmpliGraph is an open source Python library with a suite of neural machine learning models for relational learning in knowledge graphs. AmpliGraph is powered by TensorFlow and provides a user-friendly API to generate knowledge graph embeddings. Use AmpliGraph if you need to discover new knowledge from an existing graph, predict links between concepts, cluster and disambiguate entities, or use the embeddings in a downstream task.

*Click below to learn more about Accenture Labs project.

Finalist: Accenture @ The Dock
The Fairness Tool

The Fairness Tool helps organisations to assess and understand their AI-powered decision making systems to ensure more equitable outcomes. It is not a simple prescriptive tool, because ensuring algorithmic fairness is not that simple. The Fairness Tool fosters a deeper understanding of data science challenges and solutions for a broader, more diverse audience.

*Click below to learn more about Accenture @ The Dock’s project.

Finalist: CREA
Predictive Modeling of Sorghum Biomass Yields Using Fraction of Absorbed Photosynthetically Active Radiation Derived from Sentinel-2 Satellite Imagery and Supervised Machine Learning Techniques

This project innovatively implements machine learning and fraction of absorbed photosynthetically action radiation derived from Sentinel-2 constellations to predict yields of biomass sorghums ahead of harvesting. This solutions answers sorghum stakeholders’ concerns, is poised to improve farming business operations, and will help predict and stabilize prices and avoid fuel crises.

*Click below to learn more about this project.

Finalist: Centre For Cancer Research And Cell Biology, QUB
GECA

GECA was a response to a translational challenge namely how to integrate two sets of data – pre-clinical tumour models and cancer patient samples – without altering their integrity or structure. Borrowing from geostatistics, GECA was developed based on compositional statistics to compare gene expression levels without the need for rescaling. It can be considered a soft integration method which facilitates classification and quality checking.

*Click below to learn more about this project.

Datsci Innovation

DATA SCIENCE TECHNOLOGY INNOVATION
OF THE YEAR

​Our ‘​Data Science Technology Innovation of the Year’ award recognises individuals or teams that have worked together on products or solutions in the past 12-18 months which showcase an advancement of data science in industry/business. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: Logical Clocks AB
Hopsworks

Hopworks is a platform for the development and operation of AI applications. It provides unique support for project-based multi-tenancy, and horizontally scalable end-to-end machine learning pipelines, including the industry’s first Feature Store, a data warehouse for features, and HopsFS, the world’s most scalable HDFS-compatible filesystem. Hopsworks provides a web-based development environment, including Jupyter notebooks, and a REST API.

*Click below to learn more about Logical Clocks AB project.

Finalist: Rasdaman GMBH
Rasdaman

Many of our Big Data extend in space and time, such as satellite imagery, weather data, etc. Getting insights at scale remains tedious for experts and impossible for non-experts. Actionable datacubes, pioneered by Rasdaman, unleash Petascale assets for realtime intercontinental fusion, visualization, and ML at new scales for experts, non-experts, and AI tools. Recognizing this, ISO and other bodies use Rasdaman as their standards blueprint.

*Click below to learn more about Rasdaman’s project.

Finalist: Mathesia
Crowdsourcing Data Science for Safety in Industry

Mathesia together with Eni launched a challenge using Data Mining, Data Fusion & Data Visualisation & applied many innovative technologies including Natural Language Processing to incorporate textual data into the analysis & Machine Learning to perform unsupervised data clustering. Mathesia were able to define a safety roadmap and identify relevant data sources. The ouput was to create an interactive dashboard that’s useful to the HSE department of Eni.

*Click below to learn more about this project.

Finalist: Nationwide Building Society
Decision Toolkit – Unlocking The Black Box

Many people associate Machine Learning with a “black box”. In the highly regulated financial services sector, this has proven an unsolvable mystery…until now. Through the creation of a pioneering “Decision Toolkit”, Nationwide has innovatively shone a light on how to interpret Machine Learning models from both a data ethics and business performance lens. A huge step-change for credit scoring solutions.

*Click below to learn more about this project.

BEST USE OF DATA TO ACHIEVE
SOCIAL IMPACT

Our ‘Best Use of Data to Achieve Social Impact’ award recognises data science projects from individuals or teams which had a strong positive impact on social justice or environmental issues affecting their local community or the broader world around them. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: IBM Ireland Lab
IBM Traffic Analysis Hub

Human trafficking is the fastest growing criminal enterprise in the world. An estimated $150 billion was generated by slave labour in 2014 and 40.3 billion people worldwide were victimised in 2016. IBM developed Traffik Analysis Hub (TA Hub); a global data sharing and analysis platform which uses advanced cognitive technologies to gather and share human trafficking information easily and quickly. Using AI technology, large volumes of non-personal data from multiple sources is uploaded, analysed and processed while ensuring its security and integrity.

*Click below to learn more about IBM Ireland Lab’s project.

Finalist: DataKind UK
Identifying food bank dependency early

Four DataKind UK volunteer data scientists and a Welcome Centre (a small food bank in Huddersfield) trustee embedded a machine learning model in the food bank’s referral system. The model identifies clients who are likely to become dependant early in their journey, enabling them to get extra support and advice to prevent temporary crises becoming more permanent.

*Click below to learn more about DataKind UK’s project.

Finalist: Turkcell
Lost Child Finder

Globally many children are lost and need help to be rescued. Our solution uses huge signalisation data creating in near realtime a customer location cache. This predicts people who will be in the alert region and can help find the child. The solution also keeps track of notifications coming to police that a child is seen in the area and predicts potential criminals using location change activity pattern matching. The solution enabled 24 children to be saved in 2019.

*Click below to learn more about Turkcell’s project.

Finalist: Volunteer Technologists Supporting the Red Cross
Register of Pledges & Case Management System

The Register of Pledges utilises data as a means to harness public goodwill towards refugees and mid-grants by providing people with a website to pledge accommodation, goods and services for use by refugees. This database is administered by the Irish Red Cross. Further supporting technologies were developed by volunteers in the form of a Case Management System which includes the only measures of integration outcomes in Ireland.

*Click below to learn more about this project.

Finalist: Office for National Statistics
Modelling access to services by building a complex transit network

The ability for a household to access services such as pharmacies, general practitioners and schools is of great importance to policymakers. The Campus created an R package – proper – which is reliant entirely on open-source transport data to understand variation in access to services in communities. This tool is being used by the Welsh Government to understand national-scale deprivation measurements.

*Click below to learn more about this project.

Best use of Data Science/AI for Industry 4.0

BEST USE OF DATA SCIENCE/AI
FOR INDUSTRY 4.0

Our ‘Best Use of Data to Achieve Social Impact’ award recognises those making a positive impact on their industry/business in driving the Industry 4.0 agenda. Any innovative products/solutions must have been developed and used as part of a live Data Science/AI implementation in industry/business. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: Tecnalia Gestamp
NAIA I4.0

NAIA_I4.0 addresses the challenge of analysing the huge amount of data generated by the Energy Management Systems (EMS) and Manufacturing Execution system (MES) in an industrial plant. NAIA_I4.0 agglutinates a suite of machine learning algorithms and mathematical methods for transforming data into useful information, where the managers can see the energy-production details of all the plants, processes and machines and identify energy inefficiencies.

*Click below to learn more about this project.

Finalist: Accenture The Dock
XR Insights

XR Insights, allows industries to train workers in augmented and virtual reality by replicating its costly or dangerous real-life work environment and enabling better learning and reducing human error. XR Insights has a built-in streaming platform that consumes data to understand user behaviour and provide real-time feedback through AI-generated responses.

*Click below to learn more about this project.

Finalist: Telekom Innovation Laboratories
Cognitive Edge for Factories (CEFF)

Based on campus network and edge computing, CEFF enables AI/ML use cases on the shop floor for flexible production and automation in logistics and production, The solution can provide both indoor and outdoor navigation as a service for autonomous transport systems (ATS), facilitating versatile and location-flexible usage. The architecture and analytics capabilities enable further Industry 4.0 application scenarios including AR, predictive maintenance or quality control.

*Click below to learn more about this project.

Best use of Data Science/AI for Customer Experience

BEST USE OF DATA SCIENCE/AI
FOR CUSTOMER EXPERIENCE

Our ‘Best use of Data Science/AI for Customer Experience’ award recognises those that have applied Data Science/AI as part of a live implementation to improve the experience of their customers.. Revisit the projects from this year’s DatSci Awards by clicking the thumbnail images next to each finalist’s name.

Winner: Beauty Matching Engine
Personalising the Beauty Shopping Experience

Beauty Matching Engine has created the world’s 1st beauty specific personalisation and predictability software backed by AI to help beauty companies enhance their customers’ shopping experiences and sales.

*Click below to learn more about this project.

Finalist: Accenture CIO
KX Tagging Recommendation for AI Enabled Document Search

Finding the right information in an organization as large and complex as Accenture is hard. Accenture’s Knowledge Exchange (KX) supports this need by providing a searchable repository of documents. The Studio’s AI solution adds semantic tagging to make these documents more discoverable. With KX Tagging, everyone’s experience is improved, and the company goal of sharing knowledge is made more achievable.

*Click below to learn more about this project.

Finalist: Arvoia
Using Ai to Improve the Care Hire Experience

Arvoia provides an AI Cloud Platform to the Travel Industry driving proven increases in customer value over 25%. The AI must cope with some difficult constraints such as 1) Very sparse data, 2) Customers generally book once, 3) Bad historical data, 4) 95% of customers leave no trace in historical data, 5) Real time – 200 milliseconds, 6) Designed for non-technical users.

*Click below to learn more about this project.

Finalist: Zalando SE
Sorting Fashion Articles to Increase Engagement and Revenue

Many of our Big Data extend in space and time, such as satellite imagery, weather data etc. Getting insights at scale remains tedious for experts and impossible for non-experts. Actionable datacubes, pioneered by rasdaman, unleash Petascale assets for realtime intercontinental fusion, visualization, and ML at new scales for experts, non-experts, and AI tools. Recognizing this, ISO and other bodies use rasdaman as their standards blueprint.

*Click below to learn more about this project.