In this article we’ll discuss predictive analytics and how it can be beneficial, especially in the housing sector. In addition to this we’ll also cover the journey that data can go through, with a few examples of how predictive analytics can work and dive into some of the myths surrounding the technology.

Most organisations use a form of business intelligence, but this doesn’t necessarily include a predictive analytics function. What predictive analytics does is actually take your data and take it even further.

A good BI tool will allow you to create reports and run queries against collected data, and many BI tools will showcase this on dashboards with visual data such as charts or graphs.  The analytics involved in BI is often described as predictive analytics when in fact it is descriptive analytics. Predictive analytics are key to seeing what is likely to happen in your organisation. By using data mining, predictive modelling, and other analytical practices along with machine learning capabilities, you’ll be able to identify future risks or even opportunities in your organisation. With the machine learning aspect, this means that the algorithms will constantly change the results if necessary and assess and inform you of the most relevant points. This means that your data is no longer static, it will constantly be explored in different ways and the results will change depending on whether the system has discovered something new.

Predictive analytics uses statistics, probability, and forecasting to answer queries. Now the journey of data, can be quite simple, depending on who you speak to. It starts with descriptive analytics. This is the analysis of historic data to see what has happened in the past. Whether something has happened in the past week or the past ten years, descriptive analytics will give you these insights. Now this may give you an answer to your business problems, but this does take more human input and guesswork. Then we move onto diagnostic analytics. This allows you to find out why something has happened, so again it uses historic data to figure this out.

Finally we embark on the last step: predictive analytics. As mentioned before, predictive analytics allows you to take all of that data that you have collected, which tends to be a lot for organisations within the housing sector, and really drill down into it. You’ll be able to gain insights that you may never have had access to before.

Examples

Here are some examples, relevant to the housing sector, of how you can explore your data even further with a predictive analytics tool.

1. Predicting ‘No Access’ Jobs

No access jobs can be costly and something that most organisations would want to prevent from happening.

After running the data through our system, we found that ‘No Access’ jobs were more likely to happen if they occurred in the afternoon, even more so if it was a sunny afternoon and again even more likely to occur if it was a gas service job.

This information can now be used in a multitude of different ways, for example you could choose not to schedule Gas Service visits during the afternoon in the summer, but this may or may not be the best approach. Another option is to make sure you have extra contact with those customers to ensure they will be there at that time.

2. Predicting Missed Rents

For most organisations, looking at the majority may not always be the insights that you need. In this second example, we actually look into a small group that appeared in the results.

This was not the majority of customers but we found that there was a high percentage of a small group of female, divorced or widowed, over 70’s that were likely to go into arrears with their rent. When our partner discovered this, they were wondering, why there was such a high percentage of people in that small group that were missing rent, so therefore decided to reach out to them personally.

They found out that these women had somewhat recently been widowed, and that their husbands had been dealing with the finances and due to the stress of losing someone they hadn’t been able to get up to date. As a result of this, they helped these women sort out what was needed and furthermore increased customer satisfaction.

(These examples were taken from datasets from a partner with our software ROCC Focus run against some predictive models)

Predictive analytics has been used in the financial sector for some time, but it is still relatively new to the housing sector. You can used resident data to find the answers to potentially any question that you may have.

Organisations in the housing sector are sat on top of a goldmine of data. And most approaches that people take towards issues that come up is to be reactive. Once a problem has occurred, you can then react to try and resolve it. This isn’t necessarily the best approach. In an ideal world we would take a proactive approach to everything, and although we know that this isn’t always possible, it has the potential to ease workloads and keep customer satisfaction levels high. From both a customer and business perspective, being proactive can solve many issues.

Often, we base our suspicions on common sense, but may not always be the right solution. It is not too late to invest in fully comprehensive and combined business intelligence and predictive analytics tool. Make the most of your data and gain insights that will truly allow you to make informed decisions about the future of your organisation now.

If you found this article interesting and would like to discuss this further, please send me a message on LinkedIn or visit www.rocc.com

Author

  • ROCC

    Over 1,000,000 properties are maintained with ROCC Housing Maintenance and Repairs software.

    View all posts