Predicting Rent Arrears: how to improve collection rates using data analytics
Housing Authorities are responsible for housing some of the UK’s most vulnerable citizens so it’s to be expected that occasionally tenants will experience difficulties in paying their rent on time and will fall into arrears. This situation negatively affects both the tenant and housing association. Falling behind on rent payments can be stressful for the tenant and may lead to mental health issues and a build-up of further outstanding payments. The loss of revenue for housing associations can put them under substantial financial burden and unfortunately the salutation is only getting worse. As a result of the rollout of universal credit in 2013, tenants are now six times more likely to fall into arrears.
Many housing associations across the UK have as many as a third of all tenants in arrears, with further money owed by former tenants. In almost all cases, management of arrears cases is retrospective. However, this system is stretched by limited resources and is not able to discriminate between those who are likely to pay back their debt quickly and those who are more at risk of entering a state of long-term arrears, which accounts for the majority of arrears debt. But if a more intelligent system could be implemented to differentiate the high-risk cases from relatively benign, temporary ones, housing associations could make better use of their resources and be less vulnerable to persistent lost revenue.
Using predictive analytics, housing associations could identify tenants who are most at risk for going into long-term arrears. While most housing associations are yet to explore the potential of data analytics, Hackney Council are already starting to do something very similar. In a five-week data project, a team of training data scientists devised an innovative way to help Hackney Council predict those tenants who were most at risk of falling into long-term arrears. The team couldn’t identify a single factor with an overriding predictive power, so instead, they observed that subtle combinations of factors that were associated with risk. Using this insight, the team produced a predictive model that calculated the risk of arrears for each tenant. They then extended this model to predict an arrears trajectory for each, differentiating between short-term and long-term arrears risk. This then allowed the council to determine which of the arrears cases pose the greatest risk and should, therefore, be prioritised for targeted intervention.
Another approach would be to use AI which is capable of communicating with your housing management database and the scoring system used by credit reference agencies. Using this approach, you can predict and be presented with a ‘propensity to pay’ score. This will automatically adjust according to the latest information, such as whether any loans, including those from sub-prime lenders, have recently been taken out or any credit payments missed. This means that when tenants misjudge a month, perhaps because they have an unexpectedly large bill to cover, you’re able to help mitigate their situation with a reduced rent payment for that month, followed by a manageable payment plan to help get their payments back on track. If however, the indicators suggest the tenant is in more serious difficulty, perhaps if several loans have been taken out recently, you can intervene with the provision of support, such as referring them to a debt counselling service.
While data analytics and AI might seem like the ideal solution, getting to the point at which you can extract meaningful information from your data can be a long and difficult process. Having worked with Housing Associations for many years, we’re aware that housing data is almost always spread between multiple systems and integration is rarely easy or cheap but investing in ‘fixing’ this data will open far more doors for housing associations in the future – from reducing arrears to predictive maintenance, improved communication with tenants, smart homes and integration with health and social care – the list goes on.
If you’re feeling inspired (you should be) why not check out our blog, ‘Building better communities with the UK’s leading social housing providers’ to find out what inspiring concepts were conceived at our recent National Housing Hackathon.