Scroll to top
Get In Touch
V.301 Vox Studios 1-45 Durham Street London SE11 5JH
hello@decisionLab.co.uk
Ph: +44 (0)20 3735 8580
Work Inquiries
hello@decisionLab.co.uk
Ph: +44 (0)20 3735 8580

Pay,UK

BEHAVIOURAL AGENT BASED MODELLING OF BANK ACCOUNT SWITCHING

CLIENT

REQUIREMENT
REQUIREMENT

Pay.UK wanted to know how to best encourage account switching through banking innovations and marketing efforts.

CHALLENGE
CHALLENGE

Realistically modelling human decision making in complex scenarios that match real-world data and provide confidence in its predictions for what-if scenarios.

SOLUTION
SOLUTION

An agent-based simulation model of the UK banking market focusing on individual consumer behaviour, which allows ideas and concepts to be tested and assessed in a simulated world

Increasing competition in the banking sector
Increasing competition in the banking sector

The UK government had a political objective to increase competition in the banking sector. To facilitate and de-risk consumers changing their bank accounts, the government launched the bank account switch guarantee service. However, the level of current account switching remained very low and Pay.UK wanted to understand this, and to assess how future incentives might motivate switching and increase the switch rate. 

Pay.UK specifically wanted to test the impact of its idea of a "portable bank account number" – an account number and sort code that stayed with you personally regardless of who you banked with. 

Capturing the complexity of human decision making
Capturing the complexity of human decision making

Our biggest challenge was to create an accurate model involving human behaviour in real-life events. There are multiple layers of complexity – for example, how do we model the life events that are typical triggers for people to consider switching their current account. And then there is a generational factor in the decision making, as older people are less willing to change accounts than younger ones. All this is further complicated by how each person will react to a variety of news events, bank actions (positive and negative) and the marketing a person will receive both from the bank they are currently with, and competitor banks.

Can this effort be better targeted to focus first on those that we can show are more likely to get a low rating? If so, how do you prioritise? Is there a set of the indicators that can help to foresee the food establishments that are less likely to follow good hygiene standards? Are these indicators even known or recorded anywhere? Facing these questions, Decision Lab had to work with very few data available on food establishments. Going through the unstructured sources such as the scans of handwritten notes that varied between the Local Authorities was not an easy task.

Turning qualitative data into a set of hard rules
Turning qualitative data into a set of hard rules

We developed an agent based simulation model of people’s decision making when considering switching accounts, including customer awareness, the pull and push factors, etc. To understand the hows and whys of what makes people tick – their decision-making regarding their financial interests – we had to exploit the latest academic research in psychology. The qualitative research into this was undertaken by an academic partner, but we had to convert their findings about human behaviour into hard numbers and rules that we could build into the model, and get results that matched the data. By running multiple scenarios, we could assess different intervention strategies – incentives offered, marketing campaigns, implementation mechanisms and more – and determine their effectiveness at getting people to switch accounts and increase banking competition.

The bad news and the good news
The bad news and the good news

The simulation that we built showed that the main idea Pay.UK wanted to test – a ``portable bank account number`` – doesn’t work. This was important to know and Pay.UK did not introduce this to the UK banking sector, and so avoided a potentially costly failure. But our model offered much more: it provided a capability to assess and understand the potential impact of different banking innovations. This included the new ``challenger`` banks – the likes of Metro and Monzo – which were emerging at that time and predicted the effect this might have on the existing high street banks. Pay.UK use the tool to assess the impact of future banking innovations and guide their strategy.

Let’s collaborate

Send us an email, to discuss a new project.

We’re a team of innovators who are excited about unique ideas and help companies to create amazing solutions.

Finance

Pay.UK

We use cookies to give you the best experience.