Outcomes

Final reports

Telenor

About the event

Our next Data Study Group will be held Monday 2 September - Friday 6 September 2019 at The Alan Turing Institute in London.

Applications for this Data Study Group are now closed. 

What are Data Study Groups?

  • Intensive five day 'collaborative hackathons' hosted at the Turing, which bring together organisations from industry, government, and the third sector, with talented multi-disciplinary researchers from academia
  • Organisations act as Data Study Group 'Challenge Owners', provide real-world problems and data sets to be tackled by small groups of highly talented, carefully selected researchers
  • Researchers brainstorm and engineer data science solutions, presenting their work at the end of the week

Why apply?

The Turing Data Study Groups are popular and productive collaborative events and a fantastic opportunity to rapidly develop and test your data science skills with real-world data. The event also offers participants the chance to forge new networks for future research projects, and build links with The Alan Turing Institute – the UK’s national institute for data science and artificial intelligence.

It’s hard work, a crucible for innovation and excellent science, and a space to develop new friendships.

Reports from a previous Data Study Group are available on the Outcomes section of the April 2018 Data Study Group pages.

Challenges

Our challenges and data sets are provided by partner organisations for researchers to work on over the week.

The organisations and challenges leading the Data Study Group this September are:

  • Telenor - Green Radio: Dynamic power saving configuration for mobile networks
  • Turkcell - Real-time jammer detection, identification and localization in 3G and 4G networks 
  • STC - Bandwidth allocation for mobile users: a solution for rural and urban areas
  • Telus - Understanding the influences of network measures on customer perception of network reliability

Please see below for further details on each challenge

The skills that we think are particularly relevant to the challenges for this Data Study Group are listed under each challenge description below.  Please note, the lists are not exhaustive and we are open to creative interpretation of the challenges listed. Diversity of disciplines is encouraged, and we warmly invite applications from a range of academic backgrounds and specialisms.

Data Study Group April 2019 participants at table

Expenses

The Alan Turing Institute will cover travel costs in alignment with our expenses policy. We will also provide accommodation for researchers not normally London-based. Accommodation for researchers who are from a London university or research institute may be available for those who travel from outside London to work. Expenses for international applicants is capped at £200, which includes any costs of visa. Lunch and dinner is provided for participants during the week. 

Preference will be given to applicants who are available for the full duration of the week.

The Alan Turing Institute is committed to increasing the representation of female, black and minority ethnic, LGBTQ+, disabled and neurodiverse researchers in data science. We believe the best solutions to challenges result when a diverse team work together to share and benefit from the different facets of their experience. You can review our equality, diversity and inclusion (EDI) statement online

Challenge descriptions

We have been working with GSMA and through them we are presenting four challenges:

Telenor

Green Radio: Dynamic power saving configuration for mobile networks

Mobile networks waste energy by keeping too many radio-cells turned on when demand is low during off-peak. This challenge is about automating next-day power saving schemes for each individual cell tower in a country, based on current load and expected demand profile in the area. The solution should optimise power saved while avoiding negative impact on the user's network experience.  

Dataset: Time-series with two years of hourly load for about 1,000 sites in urban and rural areas of a European country. 

Useful skills: Machine learning, time series analysis, reinforcement learning, data science


Turkcell

Real-time jammer detection, identification and localization in 3G and 4G networks

In urban areas, jammers cause interruption on mobile 3G and 4G communication networks, which leads to severe service quality deterioration. This situation causes customer complaints and time and labour costs during detection studies. Based on the provided dataset, including some network service quality indicators and jammer geographical location, the participants are invited to investigate methods for real-time detection of jammer presence, identification of jammer type and its location. 

Useful skills: good data analysis and geographical data visualization skills; experience training and tuning statistical, machine learning and deep neural network models with libraries/frameworks such as sci-kit learn, TensorFlow, or similar
 

STC

Bandwidth allocation for mobile users: a solution for rural and urban areas

We want to build algorithms to dynamically allocate bandwidth over mobile networks in order to improve quality of service and speeds for specific customers in rural and urban areas. It is common for mobile phone users to purchase plans which include dedicated bandwidth. However, some of these customers may not consume all their bandwidth or they may sometimes require more allocation. STC will provide an extensive and rich dataset, which will include data about customer profiles, network consumption and mobility patterns for both an urban and a rural case study. 

Useful skills: modelling with structured data records, supervised learning, time series prediction, probabilistic prediction.
 

Telus

Understanding the influences of network measures on customer perception of network reliability

Telus regularly conducts surveys with customers to gather feedback and identify service improvement opportunities to prioritise investments in a way that reflects customers’ needs. We are therefore interested in understanding how our network and the customer experience, while using our network, influence the results of this survey. More specifically, we would like to understand (i) how accurately the customer’s experience of reliability on our network can be predicted, and (ii) what are the main drivers of network performance to influence our customer’s rating of their experience. This challenge will include a wide cross-section of anonymised data from network sources (e.g. usage metrics, KPIs etc.), non-network sources, as well as completed customer feedback questionnaires.

Useful skills: predictive/supervised modelling and time series modelling.

Find out more

How to get involved as a researcher

How to write a great Data Study Group application

Queries can be directed to the Data Study Group Team

Organisers