Brick by Brick
This regional community affairs program is about exploring solutions to complex problems in Southwest Ohio. This podcast is a companion piece to our larger project. Visit https://www.cetconnect.org/BrickbyBrick/ to learn more.
Brick by Brick
A High-Tech Upstream Response to Eviction
As evictions and the number of people experiencing homelessness remain high, keeping people in their homes could come down to an algorithm. If homeless prevention agencies got a heads up on who was at-risk and what types of bills they were having trouble paying, they could help prevent an eviction even before an eviction notice. Cincinnati and other cities are trying it. Maidstone, England has data to back it up.
Interview guests: Kevin Finn, president of Strategies to End Homelessness; Amy Riegel, executive director of the Coalition on Homelessness and Housing in Ohio; Raúl Ordóñez, University of Dayton professor of electrical and computer engineering, and more.
Ann Thompson:
There are a record number of people experiencing homelessness. National experts point to rising rents expiring COVID money and in some states a strain on the shelter system from the migrant crisis. Wages haven't kept up.
Amy Riegel:
In order to afford modest housing, a two bedroom apartment in the state of Ohio, a person has to earn $20 and 81 cents an hour.
Ann Thompson:
More than 6,000 people were unhoused in Greater Cincinnati last year. For Montgomery County it was 5,000 and there's a lag in data. What we're experiencing today, we'll hear about in 2025,
Kenny Scott:
People should care about us. You know what I mean? Just because we're homeless don't mean we're bad people.
Ann Thompson:
The family shelter, Bethany House and others are only able to help 14% of those who need it, leaving people to ask these questions as they try to avoid having to live on the streets.
Peg Dierkers:
Do I pay the utilities this month or do I pay my rent? Or do I pay what I owe on my medical bills for the serious health condition?
Ann Thompson:
Are homeless prevention agencies are doing what they can. Now they have a new idea to keep people housed, identify the vulnerable before they get an eviction notice and offer up assistance.
Kevin Finn:
This is also very much a mindset shift for a group of nonprofits that are normally used to waiting for somebody to come knock on our door before we considered helping them. Now we're going to go knock on their door.
Ann Thompson:
Strategies to End homelessness and its partners are using predictive data analytics to keep people in their homes. Today on the pod, how they're doing it, where they got the idea, and how people who aren't in this pool of assistance can be proactive with a Chatbot? Let's get into it. This is Brick by Brick: Solutions for a Thriving Community.
Ame Clase:
Brick by Brick is made possible thanks to leading support from t e Debra and Robert Chavez and Greater Cincinnati Foundation. With additional major support from AES Ohio Foundation, Laurie Johnston; Susan Howarth Foundation, the George and Margaret McLane Foundation, Diane and Dave Moccia, The Dayton Foundation, the Robert and Adelle Schiff Family Foundation and more. Thank you.
Ann Thompson:
Hi, and welcome to Brick by Brick, where we're highlighting Solutions for a Thriving Community in Southwest Ohio. I'm your host Ann Thompson. Homelessness is a big problem and it keeps growing. The US government started keeping track nearly 20 years ago and reported in 2023, there were more than 650,000 people who lacked permanent shelter. That's a 12% increase from the year before. In Ohio, it went up 6%. Bethany House CEO Peg Diker hears about people's struggles on a daily basis.
Peg Dierkers:
By the time families get to us, they've often tried living in a storage unit or in their car, staying in shopping center, parking lots overnight, usually homeless for almost a year,
Ann Thompson:
Brick by Brick talked to people who are in this situation.
Kenny Scott:
My name's Kenny Scott. I'm 51-yeasr-old. I’m homeless, no place to go. I live here under this bridge in that tent right back there, me and my brother,
Ann Thompson:
He says a car accident caused him to lose his job and now he's unable to work. He wishes circumstances were different.
Kenny Scott:
I would love to be on the lake somewhere, fishing, you know what I mean? Enjoying my family.
Ann Thompson:
We caught up with Sandra Johnson outside the Freestore Foodbank.
Sandra Johnson:
My son and I were homeless for a while. We stayed with different people and then we were just blessed and apartments started opening up and we've been doing pretty good ever since.
Ann Thompson:
Her son got financial assistance with a rental deposit and that helped them secure an apartment. In Price Hill. Her daughter found income restricted housing. Now they each have their own place. She says Communication is key. Here's her message to people experiencing homelessness.
Sandra Johnson:
Pray. Stay in your faith, and if you just stay positive, it will work out. Reach out to people. Don't be ashamed because we all have situations. Hold your head up high and reach out and get the help that you need.
Ann Thompson:
But it's not easy. When rents rise, so does homelessness. There's already a shortage of affordable housing. The Coalition on Homelessness and Housing in Ohio says for every 100 extremely low income people trying to find housing, there's only 40 units available. That creates a system where most are paying more than 50% of their income on housing. Executive Director Amy Riegel says only two of the top 10 jobs in Ohio pay enough from modest apartment. She's noticing more people are living on the streets because they can't get into a shelter.
Amy Riegel:
Individuals who we see either perhaps living in a park or in a doorway, or even in a place that's not fit for human habitation like a car or abandoned home, those numbers are on the rise. We're seeing more families entering homelessness
Ann Thompson:
In her 20 years in the field. Riegel says she's rarely heard of a family ever experiencing unsheltered homelessness, but she is now.
Amy Riegel:
It was somewhat that marker in our souls of we would never allow a baby to spend a night in unsheltered homelessness. And now we're hearing reports all across the state of social service workers going out and finding families with young babies living in a car.
Ann Thompson:
President of Cincinnati's Strategies to End Homelessness Kevin Finn doesn't want people living on the streets. Statistics show they are three times as likely to die that way. The problem is shelters are packed and it's expensive to house people in them. Finn says it's much more cost effective to keep people in their own place with assistance from his agency and others. It's just $1,600 to help someone find an apartment who is sleeping on a friend's couch compared to $4,700 to secure housing once somebody is already out on the street. What if we could stop homelessness before it happens? Finn and others are trying something different to keep people in their homes. Predictive data analytics, developing algorithms and plugging in data to predict things is nothing new. The healthcare industry uses it to improve patient care. Banks use it to predict whether somebody is too big a risk for a loan, and Amazon uses it to suggest what people might want to buy next. Kevin Finn wants to predict who is most likely to become homeless before they do and offer up assistance to keep them housed. As you might guess, the more data points, the more accurate the prediction. He's identified 40 different types of data to plug in, including utility shutoff notices.
Kevin Finn:
We already have about a half dozen that we're using, and it's everything from some historical data of people who previously experienced evictions previously were homeless, had called the helpline that people call for the central access point helpline that people call for information about housing resources. We have data from St. Vincent de Paul about people and services that they have delivered.
Ann Thompson:
The data is fed into an algorithm that University of Cincinnati economist Gary Painter, will update every few months. For privacy reasons, the information is anonymous to everyone except social workers. They're given the names of people the computer says need the most help. Then they work to provide financial assistance and if necessary, a new place to live. The City of Cincinnati partially funded this effort with a two year, $2 million grant. Finn anticipates being able to help 160 families a year. The program started in July. Finn says, many people just need a leg up.
Kevin Finn:
I've never met a person really who's homeless for just one reason. I mean, typically it was the interplay of two or three or maybe even four things that all sort of went wrong.
Ann Thompson:
Brick by Brick’s, Hernz Laguerre Jr. met a woman who fits this category and could have benefited from predictive data analytics if the program was available when she needed help. Hey, Hernz, tell us more about this program.
Hernz Laguerre Jr.:
So you remember during episode five when we were covering right to counsel and we all agreed that it's a downstream solution. Sure, you don't get counsel until after you're evicted and are facing homelessness, but this program has a potential of being an upstream solution of intervening before the eviction notice is even written and homelessness is even considered because the program has just recently launched and it's still developing. I wanted to use a real situation that happened to a resident to see how this program would've intervened for her. Take a listen.
Tender Smith:
You really got to work like six jobs to make a living and stay afloat.
Hernz Laguerre Jr.:
Tender Smith is a single mother of four kids working one job as a medical assistant at Centrum. She's faced financial hardship and has been evicted before.
Tender Smith:
A lot of landlords don't, they don't know who living there. They don't know what you really going through for real, they just be like, oh, you late up, put her out. In all actuality, they know there’s nowhere to go out here.
Hernz Laguerre Jr.:
How do people find themselves in these vulnerable situations? Kevin Finn, CEO of Strategies to End Homelessness shares how
Kevin Finn:
Homelessness and eviction or people being at risk of eviction tend to be caused by pretty short term crises. A lot of times it can be as simple as can't get to work because the car needs a repair or all sorts of things like that that are fairly short-term issues,
Hernz Laguerre Jr.:
Unexpected life events can happen to anyone, and when you lack resources, those events put you at a greater risk of homelessness. The agency Strategies to End Homelessness is working on a solution to step in right when those unexpected events happen.
Kevin Finn:
Okay, let's catch people before they lose their housing.
Hernz Laguerre Jr.:
With the help of funding through the City of Cincinnati's. Impact Award Strategies to End Homelessness is the lead agency in a new system called the Cincinnati Family Housing Stabilization Collaborative. This program uses data analytics to prevent homelessness.
Kevin Finn:
Let's find people before they have an eviction notice in their hand and head off their sort of new or emerging crisis as early as we can. My experience has been that the further upstream you go with these prevention activities, it costs less to help them and you get better outcomes for your investment.
Hernz Laguerre Jr.:
The way this works is that data is collected from multiple sources such as Hamilton County, the City of Cincinnati, and organizations alike masking the names that the data belongs to For privacy, the data is used to build a profile on a household using information that shows that they use emergency rental assistance or applied for services at places like the Freestore Foodbank. Then it gets plugged into an algorithm to see who is likely to get evicted. Once the system flags person that is at risk, they are identified.
Kevin Finn:
We're looking for people that the data tells us are most likely to receive an eviction notice, and then our partner agencies are going to proactively reach out to those families and offer them assistance.
Hernz Laguerre Jr.:
Bethany House is one of the partner agencies because the program is new and is still collecting data. I presented to them Tender Smith’s situation to see how the program would've intervened.
Tender Smith:
I had a medical issue going on where I had to get blood transfusions and iron infusions weekly so I couldn't work full time.
Hernz Laguerre Jr.:
And a recent bill forced her to make some tough decisions.
Tender Smith:
They send out water bills every three months. I got my first water bill and I was like, oh, hold on. I didn't factor that in, so I was kind of late on my rent,
Hernz Laguerre Jr.:
But Tender is determined to stay on top of her bills.
Tender Smith:
I don't see myself getting evicted again or going through that again. I be so serious about my rent, I go broke. I pay my last just to not put my kids through that situation again. But at the same time, it is like she'll be times like, well, what we going to eat today? Because I just gave all my money to up for my rent.
Hernz Laguerre Jr.:
Lavanya Leonard is the director of housing at Bethany House. I asked her if the system would've flagged tender situation.
Lavonya Leonard:
We believe the system would have alerted her, but being able to see whether it be county funds or federal funds if there is income that she would be eligible for. So the system navigator would have that inside Knowledge to be able to connect her to the appropriate services. A service that is available to tender that's just out there in the ether that she's not aware of.
Hernz Laguerre Jr.:
With the program based in prevention. Imagine the difference it could make to people in similar situations to tenders.
Lavonya Leonard:
Tender’s situation is not unique. I've been in this work a long time. A lot of stories that kind of sound like Tender’s that if we could have caught them much, much sooner on the front end, she may have never needed to come into any type of homeless services.
Hernz Laguerre Jr.:
A big part of this program is having the most recent contact information for the household. So another phase of this program to be released is called Tenant Guard, and it will allow those at risk to register themselves in the system.
Lavonya Leonard:
Having the right players, getting as many people as involved as we can to have the right conversations and be able to dump the right data into the algorithm to say, yep, Hernz, we need to get Hernz help right now. We need to connect the dots for Hernz to these different entities. I think that's the key.
Hernz Laguerre Jr.:
And when asked if the Cincinnati Family Housing Stabilization Collaborative would've helped her, Smith expressed,
Tender Smith:
If they can jump in before it reached that point and tell you like, here do this, boom, boom, boom, bam, and prayerfully stop it from escalating somewhere else, that support will really go a long way.
Hernz Laguerre Jr.:
And the support in housing can help her shift her focus from her struggles to her aspirations. What would you say is the feeling or the thought that goes through your mind most of the time?
Tender Smith:
On a regular day to day, what really be on my mind? I really would like to get myself together. I want to go back to school, get a career, make more money. I really just want better for myself, but it's like, man, it's really hard to get ahead right now. I think about it every day. I woke up thinking about it this morning, what can I do to get out of this situation.
Ann Thompson:
Back in the studio now. Thanks for that Hernz. So what we've been hearing about for people in this space is that it's just not usually one big thing that happens to somebody that puts them out on the streets. It's a bunch of little things like let's say there's an increase in their water bill or their rent goes up,
Hernz Laguerre Jr.:
And I think that is the biggest thing I want people to walk away from. That's the point. I want to emphasize. Those little things that you mentioned like the water bill, electric bill or other utilities, and increasing those could cause someone who is tied on funds to miss out on their rent. And that's why programs like this are trying to reach out to Duke Energy. They're trying to reach out to the Public Utilities Commission of Ohio in order to get more information, get more data to create a clearer picture of who needs help. It's data analytics. It needs data in order to be successful.
Ann Thompson:
Yeah, it makes sense. And there is one other thing that you referenced in your package. It's called Tenant Guard. This is a way for people to self-identify if they're having problems paying their rent and are unlikely to get picked up by the predictive data analytics system.
Hernz Laguerre Jr.:
And I think this is great because there's no way the program can account for every single person that needs help. That's a large task. So this is a way to self-report and to also update your most recent contact information and potentially get help.
Ann Thompson:
And so here's how the Tenant Guard website is going to work. It uses artificial intelligence to look at the information they provided about their housing situation and suggest resources to them that are available besides what they're doing that maybe they didn't know about.
Hernz Laguerre Jr.:
Yeah, I think it'd be really helpful.
Ann Thompson:
Alright, thanks Hernz. We'll talk to you later for the takeaways.
Hernz Laguerre Jr.:
Sounds good.
Ann Thompson:
Coming up on Brick By Brick, the use of predictive data analytics isn't just a big idea. It's a proven concept. Where Strategies to End Homelessness got the idea and a University of Dayton professor gets his students involved in helping to reduce homelessness in Montgomery County.
Raúl Ordóñez:
Society is composed of systems as well, larger complex systems, but you can also approach it as a system that could be studied, analyzed, and perhaps affected by interventions.
Ann Thompson:
That's coming up on Brick by Brick.
Ame Clase:
Brick by Brick is made possible thanks to the generous support of so many, including Murray & Agnes
Seasongood Good Government Foundation, Rosmary & Mark Schlachter, The Camden Foundation, Patti & Fred Heldman, DeeDee & Gary West, The Stephen H. Wilder Foundation, Judith & Thomas
Thompson... a donation in memory of Frank and Margaret Linhardt, and more. Thank you. We couldn't do this work without you.
Emiko Moore:
Hey, it's Emiko Moore from Brick by Brick. Our new podcast is about finding solutions that will allow our communities to thrive. What does a vibrant and engaging neighborhood look like to you? Maybe it has more restaurants, coffee shops and art galleries, more multi-generational park activities, or a livelier music scene. We want to know. Please go to the Brick by Brick show page on cetconnect.org or thinktv.org. Just click on the green audience button and tell us what a thriving community looks like to you. You can also email us at Brick by Brick at publicmediaconnect.org. Imagine big and wide, get creative. We can't wait to hear from you and thanks.
Ann Thompson:
Welcome back to Brick By Brick. How successful is the use of predictive data analytics to reduce homelessness? Here's an example. A data scientist in Spokane, Washington worked with a local utility company. He studied whether anonymized utility bill data could predict a person's financial status. Smart cities dive.com reports his model linked that utility data with information Spokane provided on the use of shelters and assistance programs. With a nearly 75% accuracy, he predicted who would eventually experience homelessness. Here's an international example, Maidstone England, population nearly 200,000 is 32 miles southeast of London. Its biggest industry is paper. In 2018, after a 60% increase in homeless numbers in a five-year period, Maidstone decided it needed to do something. The Borough Council reached out to technology partners, EY and Xantura to build a predictive analytics platform. Head of Housing John Littlemore spoke to Ernst Young, whose name has been shortened to EY for this promotional video.
John Littlemore:
We were aware that this had been used in the private sector before, but this was a new initiative to take forward in the public sector to see how we might improve the outcomes for our residents.
Ann Thompson:
Just like the other examples, the system aggregates data from many different sources that produces a case summary for frontline workers who can then help people who are most at risk of becoming homeless. This data gives caseworkers a lead time of at least eight weeks before somebody has to go into a shelter or is out on the streets.
John Littlemore:
What came out of that was quite stark of the households that were assisted, less than 2% went into temporary accommodation, whereas the group that were not assisted was nearly 20%.
Ann Thompson:
With this system, Maidstone says it reduced homelessness by 40% and it's where Cincinnati's, Kevin Finn initially got the idea to try this here. Littlemore says Homelessness doesn't just affect people out on the street, but everyone,
John Littlemore:
And we know that there is a wider societal cost to that, education. job prospects are all harmed when people are in unstable housing conditions.
Ann Thompson:
Want closer examples? South Bend Indiana is also reducing homelessness with predictive data analytics. The city worked with researchers at Purdue University to build a model using code enforcement data, utility bill, delinquency, evictions, and foreclosures. Some data it had to pay for. Los Angeles County has served 700 clients since 2021 and 86% are still housed. When it comes to this solution, using predictive data analytics to intervene upstream from the problem, there are limitations. The funding. COVID money pays for California's program. That funding is expected to end in 2026. Cincinnati's predictive data analytics program is funded by a two year grant from the city. Kevin Finn says there are far more families who need help than money to go around. He continues to line up sources. Another limitation is reaching people who need help. They might have a different phone number or address, or they might not want help. Finn also struggles with getting enough data sources. Some agencies and utilities are not providing information. He hopes that changes as Cincinnati gets its program off the ground.
There's a smaller effort underway in Montgomery County, University of Dayton, Professor of Electrical and Computer engineering Raúl Ordóñez started a class called Engineering Systems for the Common Good. The idea is to produce models using data to help solve social problems. This is similar to what he does with robots. A dynamic model is a mathematical representation of how objects and their relationships change over time. Right now, the class is focusing on reducing homelessness.
Raúl Ordóñez:
So what if we spend more money on, say, more prevention or on permanent housing? So what would happen then so that ideally then the county could take these models and then start to study policymaking in a more systematic way
Ann Thompson:
Ordóñez hopes to collaborate with other agencies to better understand factors outside of the homeless system. For example, things that put people at risk of becoming homeless who aren't yet.
Raúl Ordóñez:
So for example, number of people incarcerated, people who leave the jail system who come back. Maybe people who are at risk of having a health crisis, who have low income, high rents, that kind of thing. So this data are kept somewhere. I'm sure
Ann Thompson:
During his upcoming sabbatical, Ordóñez hopes to gather that information to make a more complex, larger scale model. He would like to learn more about how Cincinnati's predictive data analytics program works. In the meantime, he's also working on a system to help cities avoid food deserts, studying the effects of things like transportation, inflation, quality of the stores and other factors.
Raúl Ordóñez:
Right now it's a very abstract kind of model. Eventually we would like to be able to represent an actual city and have something that somebody can look at and say, oh yeah, that looks like Dayton. And what if we did this? What if we change this highway or the bus line here, for example? What would be the effect of that?
Ann Thompson:
One reason Ordóñez is interested in this and preventing homelessness is the poverty he saw while in his native Ecuador and his students are realizing they can make a difference. At least one is going to graduate school to study more about the use of human rights in engineering.
Remember, if you want to learn more about how predictive data analytics is being used to reduce homelessness, there are plenty of resources including web articles, Hernz’s and Emiko’s video and audio stories and online extras. Go to cetconnect.org and thinktv.org. While you're there, click on one of the big green buttons to give some feedback or answer our current audience question. We'd really like to hear from you.
This is the time we compare notes about the episode. It's called The Takeaways. We welcome Hernz Laguerre Jr. back to the studio. And say hi to Emiko Moore. So as I thought about this episode, obviously the human element is the most important, but cost is also a factor. And I wanted to call out that the National Alliance to End Homelessness says the government spends on average $35,578 per year for every person who faces chronic homelessness. Now, this is not just the cost of the shelter, but it's the cost of publicly funded crisis services, including jails, hospitalizations, emergency services. But this 2017 survey also points out that those costs can be reduced by almost half when the person is placed in supportive housing. And one other thing, Kevin Finn, with Strategies to End Homelessness said if his organization can help people who are couch surfing find a permanent home before they're out on the streets, it costs $1,600 compared to $4,700 if they're already unhoused.
Emiko Moore:
And that’s a huge amount of money that a community can save. And this data analytics is a real shift in the mindset for a lot of these frontline workers. The case workers who are going in used to reacting to a situation. Now they can go in and do prevention. They can get a real-time snapshot of a lot of data for this family. And if you think about it, if they had to go and meet this family once the situation happened, just assessing, ingesting all of that information, how much time that would take just to get their finances, their bills, their medical records, their court records, all of that stuff would take a lot of time. And Maidstone says, you are getting about an eight week head start, which is huge. And you could also probably pinpoint a lot of the problems. Not only that are about to happen, but probably further up.
Ann Thompson:
So true.
Hernz Laguerre Jr.:
Yeah. But that's the thing though. We are a very reactive society. We are not proactive. We see a whole bunch of people who are homeless, and our answer is more shelters. And I have the same feeling in this episode that I did after the Right to Counsel episode. If these programs save money, why don't we invest all the money into it? And I think that in and of itself is the limitation, the fact that there is a need for investment and there's also a need for patients in order to get the return on investment. And sadly, we just don't operate that way because we have leaders with term limits who need to invest into things that will have a quicker return. It appears that that may be one of the reasons why there isn't a quick rush to invest into programs like these
Ann Thompson:
And to answer your why possibly is because maybe we didn't know how to do it.
Hernz Laguerre Jr.:
True, true. Yeah. That could be a possible reason too. So yeah, who knows? I think with more evidence, I think people may come on board in order to support programs like this.
Emiko Moore:
And with Maidstone that has a 40% decrease. Those are huge, huge numbers, 40%. And I also think that Amy Riegel said something that really I've thought about a lot and is a huge red flag. They're starting to see families with children who are unsheltered and across the state, and that's just a huge red flag that we really need to start paying attention to for sure.
Ann Thompson:
So If we could do something like you said, Hearns upstream, that would really be beneficial. A
Hernz Laguerre Jr.:
Hundred percent.
Ann Thompson:
Thanks for your insights, guys.
Hernz Laguerre Jr.:
No problem.
Emiko Moore:
Thank you.
Ann Thompson:
Coming up on the next episode of Brick by Brick, an effort to green up the largest African-American homeowner community in Cincinnati.
Sister Barbara Busch:
We don't want to be behind the curve. We'd like to be ahead of the curve.
Ann Thompson:
And this is only the beginning. Working in Neighborhoods and its partners are building new income- restricted sustainable homes in the Net Zero Urban village and retrofitting others Brick by Brick travels to South Cumminsville to get a closer look. That's next time on Brick by Brick.
That's our show. If you like what you hear, please rate and review our podcast. It makes it easier to find. We hope you learn something, and if you did, please tell your friends and family about it. For Hernz Laguerre Jr. and Emiko Moore, I'm Ann Thompson. We'll be back soon with more solutions. Take care.
Our show is produced, hosted an edited by me, Ann Thompson with reporting and story editing from Hernz Laguerre Jr. and Emiko Moore. Our Executive producer of Mark Lammers. Our show consultant is Gloria Skurski. Gabe Wimberly is our audio engineer and mixer. Zach Kramer runs the lights and cameras. Derrick Smith is our production specialist and Jason Garrison is our production manager. Kellie May heads up our marketing and promotions, along with Mike Shea and Bridgett Dillenburger. Elyssa Stefenson handles the website and Steve Wright is our designer. Bill Dean and Andres Kruza are the engineers for the show and our Chief Content Officer is Colin Scianamblo. Our music is from Universal Production Music. Brick by Brick: Solutions for a Thriving Community is a production of CET and ThinkTV, Southwest Ohio PBS member stations.