Speaker 1 (00:04):
This is the data science conversations podcast with Damian Deighan and Dr. Phillip Diesinger. We feature cutting-edge data science and AI research from the world’s leading academic minds and industry practitioners. So you can expand your knowledge and grow your career. This podcast is sponsored by Data Science Talent, the data science recruitment experts. Welcome to the Data Science Conversations podcast. My name is Damien Deighan, and I’m here with my cohost, Dr. Phillip Diesinger. On our last show, we discussed the amazing work that Peter Diamandis’ XPRIZE Foundation are doing. Specifically, we talked about the AI XPRIZE, which aims to accelerate the adoption of AI technologies in solving some of the world’s most pressing social problems. That prize was sponsored by IBM Watson, and 147 teams from all over the world battled it out over a five-year period with a first prize of $3 million US dollars.
Speaker 1 (01:10):
And if you haven’t listened to that episode, please do check it out. However, today is the follow-up conversation where we talk to one of the three finalists of that AI XPRIZE and our special guest today is Arnon Houri Yafin. He’s an Israeli entrepreneur who is the founder of a company called Zzapp Malaria. By way of intro, Arnon’s undergraduate degree is in economics, and he has also spent four years as a lecturer in statistics at the Hebrew University. Then between 2010 and 2011, he worked for the Israeli Securities Authority on regulation of the stock market as it relates to market concentration. From there, he joined Sight Diagnostics who specialise in machine vision based blood analysis to deliver malaria testing at scale. He started life there as an Algorithm developer, and then led the biology team and clinical studies as their Director of Research. In 2016, he founded Zzap Malaria, a startup whose mission is to eradicate malaria. Arnon, we’re delighted to have you on the podcast. So thank you so much for joining us today. Thank you. So if we start with your personal journey Arnon, could you tell us how you ended up working in both AI and in the field of malaria eradication?
Speaker 2 (02:35):
I have two answers. One is a personal story, which is just my friend took me there and then another one is poverty. So let’s start with poverty. Poverty is a horrible thing. And this is something I understood at a young age and I learned economics. My goal was to be an economist in the context of developing countries and specifically African countries because, if you just manage things better, they can be better. Then I started my MA and just before finishing the MA, a friend called me and told me that he is starting a company that is dealing with malaria. And I knew that malaria is huge problem in terms of public health. It actually kills people and not only kills people, but also a lot of other damages, but also malaria is one of the primary reasons for poverty. So it’s actually because of poverty as if you, if your house, the quality of the house is not good enough, so you have more mosquitoes in the house, but it also causes poverty. Because if you don’t show up to work, if your children don’t go to school, they will not know that. But one of the primary reasons why children in Africa don’t go to school is because of malaria. And this obviously connected to poverty. So because a friend from high school suggested and started this idea of Sight Diagnostics and because what they wanted to do, which is tackle poverty.
Speaker 1 (04:08):
I read somewhere that you made a trip to India and you saw the the devastating impact of malaria there. Could you briefly give us an overview of the impact that had on you?
Speaker 2 (04:18):
So when I worked at Site Diagnostics, I led clinical trials. They have their malaria diagnostics device that we developed, and we did it in public hospital in India, in a city called Mangalore in Karnataka and Mumbai. So in India you have some places with a lot of malaria and other places without. I was in an area with a lot of malaria. I’m kind of nervous parent when my children have a fever, I kind of lose it. But then you see the mums with young children, very feverish, the children, very feverish and they are scared, because it’s not only fever that will pass tomorrow, it’s malaria. And when I saw that, it’s kind of sharpen me the difference between malaria diagnostics to malaria elimination. Because in many countries, malaria was a problem and specifically in Israel, it was big problem. And they eliminated it mostly in the twenties, and the thirties of the last century. And the way they eliminated it is by targeting the stagnant water bodies where the Anopheles mosquito breed. So if you say you have such a big problem, but it could be fully eliminated, so why don’t we do it? This is what caused me to say, okay, diagnostics is very important, but they want something more radical. How can we recreate the success of malaria elimination done by many countries, Cyprus Egypt, part of Brazil and take it into a modern Africa.
Speaker 1 (05:50):
Is that why specifically you founded Zzapp Malaria?
Speaker 2 (05:52):
Exactly, exactly. Zzapp Malaria is about let’s move from malaria control to malaria elimination. And while moving from control to elimination takes artificial intelligence and data. So when people try to treat water bodies in Africa, they did it in partial success. And the reason is you just have wide areas. So people use, you know, house here, house there and alot of water bodies because you just have a lot of friends. And then also monitoring the operations is very difficult. One person, you send people to the village, but you don’t know exactly where there’s this kind of the north part of it, the south part of it. And then we know that the way to eliminate malaria is by treating all of the water bodies. You know, it’s very similar to COVID. If you vaccinate 90% of the population you are successful. And if you vaccinate only 60 or 50% of them, you still have COVID. Yeah. So same thing with the malaria, but not with vaccination, but with stagnant water, but you need to reach a very high percentage and this is very complex operation. And what we understood is a way to manage such complex operation is to understand and see what happens and for that, we need to digitize it. So with our system, every field worker, when going in the field, he goes with a smartphone and the smartphone shows him which water body already sprayed, which didn’t, which it should be same period, which areas who should be scanned, which houses should be sprayed, so we know everything. Yes. Everything that’s happened and this is how we get this thoroughness, and I would say perfectness of having all of the water bodies.
Speaker 3 (07:38):
Yeah. So this is super interesting what you’re telling us, very fascinating. Maybe we can go a little bit deeper into some areas. So Damien asked when we started, or when you started Zzapp Malaria. Your friend called you up, they had the project. Yeah. How do we envision this? Did they have like a concrete idea already? Did they have a team? How did you start this up? Where were you when you started the company?
Speaker 2 (08:00):
My friend is from Site Diagnostics, yeah. So my friend called me to join Site Diagnostics. He was founder with three founders, and then they asked me and two other people to join. And together we started the site diagnostics, which is about using ??? to diagnose malaria. Around 2016 I moved from malaria diagnostics insight to malaria elimination.
Speaker 3 (08:23):
So there were three of us, sorry, three of you at the beginning. Yeah. And what were the backgrounds of the other two?
Speaker 2 (08:30):
So, one is it came from Mobileye. One did his post-doc in Harvard, two actually did their post doc in Harvard, about using new technologies to detect the bacteria and other microorganisms, and then together they unified their knowledge to detect malaria in the blood.
Speaker 3 (08:52):
So you had a diverse set of skills when you started out. Yeah. And then when you started out, did you have a very concrete idea already? So you said there were two researchers involved from Harvard, they must have had previous experience, right? And this initial idea that you had you still followed up in the end or did it change over the process of building it out into an applicable solution?
Speaker 2 (09:12):
Mostly we sticked with the original idea, obviously brand new things and changed things a bit, but yes, same idea is still with us.
Speaker 3 (09:22):
That sounds interesting, yeah. So, you stuck with your original ideas who basically came together more or less to implement it and to turn it into reality rather than to do a lot of research, right? Yeah. So you started out this company, you said in 2016, I think. Is that correct?
Speaker 2 (09:36):
In 2016, yes.
Speaker 3 (09:39):
So can you explain a little bit about how the company has grown, how the project has grown over time? Also a little bit about how you got investors attracted to it, how you grew the team and so on. And then how you kind of started realising your idea. You probably had to find partners in African countries basically where you could work and communities that you could work with. So maybe start a little bit with the team so we can get a feeling for how that has grown and then we can go a little bit more into the practical aspect of how to test the research in the field.
Speaker 2 (10:09):
Our thing is now it’s six people – machine learning software, public policy and the biology. Sight Diagnostics was the first investor and then we got also grants because, in our area, it’s not very easy to get investors. Because only few investors understand how to operate with governments. They prefer startups with B2C or B2B model where they sell to direct consumers or to other companies over B2G. And for us, it’s important to find VCs which know how to engage with government and specifically African governments. So, in the first stages we used grants. So we had the collaboration with great scientists from the UK, including Andy Hardy. Together, we operate in Zanzibar. We are funded by the Bill and Melinda Gates Foundation. And what we do there, we use also drones to map the water bodies. So we fly drones over Zanzibar together with the government, obviously. And then we make the mapping faster and more perfect. So this is one grant and we had other grants. And now we have the prize money, that $3 million, and this is a significant improvement for us and now we will increase the team. You asked also very good question about partnership with African countries. So here we have two routes. One route is the professional one. So we just go to conference, malaria conference, and speak with people and explain what we do and find interested partners and then we worked in Ethiopia, in Kenya and in Ghana. And the other route, which we start to explore now is to go to the ministries. So you go to the Minister of Health and then propose what you have.
Speaker 3 (12:05):
Can you explain what’s the core idea that you had to combat the spread of malaria, right? So if I understand correctly, it has to do with identifying stale pools of water, yeah. You already mentioned that you used drone technology for instance, to use that. Yeah. The prize was also given to you by exceptionally innovative use of artificial intelligence, yeah. Maybe talk us through what’s the core idea. How do you prevent the spread of malaria?
Speaker 2 (12:32):
So in the past, the best solution to fight malaria was treating the stagnant water bodies. But today in Africa, most countries prefer the bed nets. So you just give people bed nets, and then they sleep with bed nets over their head. And it’s very, it’s a good thing. Yes. It’s protect the people, but it’s like, you know, like put mask against COVID, it’s partial protection, it really depends on a coverage. So, so many people.
Speaker 3 (13:01):
Yeah. It’s not fixing the root cause. Yeah, exactly.
Speaker 2 (13:04):
And we want to take the old and good method, but we should apply it in Africa and, to apply it in Africa, you must overcome two problems. One is coverage, you need to find all of the water bodies. And the second one is budget because you don’t have the money to, you know, to scan every single square kilometer in Africa. So based on satellite imagery, topography rain data, we tell when and where to scan for water bodies. And this is how we make that operation cheaper. And then with the mobile app, it’s about coordination and monitoring. We make sure that every parts that we, that the system decided to scan, the field workers actually scan it. Because if I ask you now, five people go and I don’t know, for example, if you are based in specific university, go and search for your university for all of the water bodies. You miss some yes, because you don’t know where you already visited and you don’t know where your team member visited. And we did a randomised trial where we show that without the app, people miss around 30% of the water bodies and without they just find them. So it’s about thoroughness.
Speaker 3 (14:21):
So you’re basically saying that using satellite data, and then also artificial intelligence, you can pinpoint people in much more precisely to those water bodies that need to be treated then. Right. And by increasing the spacial distance coverage, basically you can eliminate malaria better. So what was the idea initially? So how do you scale this across a continent like Africa? So, right, you’re still, you said you were six people – now you recruit workers in the field locally, or how does it work?
Speaker 2 (14:50):
So it’s about finding a local partner, because our core knowledge is about software and about biology it’s not about project oversight, yes. And then you should find a partner. It could be government, Minister of Health. It could be big NGO. It will be local company that want to fight malaria thats because local companies in Africa do it. And then when you find a partner, they are the ones that hire the people that go around and spray water bodies and spray houses and everything.
Speaker 3 (15:24):
So you are bringing the technology, they are bringing the people basically to make it scalable then?
Speaker 2 (15:30):
Yeah. We bring technology and we also bring knowledge about which agent to put in the water. So we are experienced because we did it once in one country then we go to new countries so we can share our knowledge.
Speaker 3 (15:46):
And you already mentioned satellite data. There’s obviously a lot happening in that space at the moment. Can you talk a little bit about which kind of data that you’re using and how you’re using the satellite data?
Speaker 2 (15:55):
One of the challenges that we had is about resolution because if you have big water body, you just see it from the satellite imagery and then it comes kind of a standard machine vision problem and you have also the near infrared, a channel where water is very distinct. Then sometimes you have water bodies, which are smaller than your resolution. So then it’s not about finding the water bodies, but about saying some area is suitable for water bodies. This is interesting because if you go to look at something smaller than your resolution, the context becomes very important. So for example, if it’s very close to big river. So big river, you don’t have malaria mosquitoes in it because it’s not standing water, but maybe around the river, you’ll find more water bodies, more stagnant water bodies. We started by having kind of small neural network that will detect only what we want to detect but then we were aware that we should use larger network so that we, it gets better usage of the context of the area. And with topography it’s also similar because in topography you have, and this is even not artificial intelligence, it’s more traditional models of topography. So you have a water, obviously go from high area to low catchment, and then you can understand that it’s not only the absolute height of specific point on the map. It’s also how, how it relates to other point in the area. And we use both traditional models of topography, but also just put it into a neural network. And again, if you give it to more area it just works better.
Speaker 3 (17:42):
So you mentioned you’re using conventional neural networks, basically to identify areas where there could be water bodies, yeah. What are the inputs for those models? So you mentioned satellite data, but you’re not only using visible light channels, but also infrared anything else?
Speaker 2 (17:56):
So it’s satellite data and then typography and also land use. It might be just someone that analyze other satellite imagery. Yes, but it does, as I said, we also use rain and humidity. And for that, IBM Watson as part of the prize, not only they gave us the money, they also helped us in machine learning projects. And they focused on the temporal part of it. Yes. Because what is not only where they are also when. Obviously in the starting of the rainy season, you will find many more water bodies than after the dry season, in the dry season they evaporate. But based on that exact amount of rain and humidity and temperature, you can predict it better. So this is something else.
Speaker 3 (18:49):
So that’s quite a sophisticated modeling that you’re doing there already. For the data sources, are they open source or do we have to buy it this kind of data?
Speaker 2 (18:56):
This is something up to the country because you have free satellite imagery produced by the European Union, but you also have high resolution satellite imagery that you can buy. This is something we help countries to get decision to understand like the pros and cons of each. Just with our limited resources until now we mostly focused on the low resolution part because yes, it will be more convenient for many of our potential customers. We need to have more experience with the high resolution satellite imagery.
Speaker 3 (19:36):
So then, so you have basically then this model that takes all of this input data and then predicts where water bodies could be. And that information goes in through an app to the workers in the field. Is that correct?
Speaker 2 (19:48):
Yes. So, so we have one more layer, which is about locating the houses. Because if you have the water body in the middle of the jungle, you don’t care because malaria is actually something that is transmitted from person to person. The mosquito is only the vector. Then if you have mosquitoes in the middle of the jungle, they just don’t care. So, we have one component that maps the water bodies and then one component, they map the houses. And then the last component is about the proximity of houses to areas that potentially have many water bodies in it. And then, based on that, and based on their allowed budget, we define where to scan for water bodies. And then we have one more component that just takes it to use the mobile app, as you just said, because the few workers for them, they see it as tasks.
Speaker 3 (20:44):
And so these workers, what do they then do, right? So they take the app, they take the information, they go to these locations and then they treat the stale water bodies with chemicals. Or how does it work?
Speaker 2 (20:56):
Yeah. They search for the water bodies. If we found water bodies from drone or from satellite imagery, we just direct them, but they can also report water bodies from the field. And this is important because this is how we feed the system. It’s machine learning, yes, we need new data. This is one thing. And then they treat the water bodies and treatment of the water bodies in the past, they use chemicals to do it, but it’s not a good thing to do, yes. Because water bodies, you know, cows drink from the water bodies and goats and sometimes even people. In today, The World Health Organisation have very strict regulation about which materials you can put into the water but mostly we use biology agents, which is called BTI and the good thing about BTI is it doesn’t affect people. It doesn’t affect cows, even frogs. It’s only mosquitoes and black flies and believe me it’s a good thing to kill mosquitoes and black flies. Not only those that transmit malaria, but also those that transmit dengue or river blindness or other yellow fever. Yes. So it’s very environmentally friendly.
Speaker 3 (22:05):
Can you talk about some specific user cases or field tests that you did with communities?
Speaker 2 (22:10):
One interesting thing that we’ve done is NGO in Ghana. They fight malaria in their town and in the villages surrounding it and they were very successful before us. They sprayed all of the houses and alot of education because education is also important so people use the bed nets and go to doctor if they have fever. And they want to push it to zero and then they approach us and together we implemented a operation against the water bodies, as I said, and the very interesting part, what we managed to reduce more than 60% of the mosquito population in the town and the villages. So it was a controlled trial in some area we treated in some areas we didn’t, and we compared the impact. And the interesting thing was that we did it only in 20% per person protected, which is extremely low. So other intervention cost them, let’s say $5 per person protected and the good thing about that, it allows us to use it tomorrow. Yes. So we did the 100 days intervention, but because it’s so cheap, we can do whole year intervention and we can enlarge it to more villages. One more interesting operation was in Ethopia where we worked in a few villages and we mapped the area. And then we learnt a lot from this operation because we saw they have different fields. So they grow teff, you know, what teff is it’s a kind of bread, but bitter. And they have a corn, for example. And we not only scan the area for water bodies, but also map it for which specific agricultures they use. And we learned the correlation. So for example, in the teff fields, they didn’t have any water body good for Anopheles mosquito for malaria. While in the grazing area, where the cows were, we saw hundreds. Because now we know the importance of using land use. So it’s not only about how God created the land, it’s also about how people use it that tell you the chance of finding water bodies.
Speaker 3 (24:19):
So it’s interesting. Yeah. So how does the collaboration work? Do you, do we have to be in the field when you work with these people in Ghana, in Ethiopia, or is this like a remote collaboration?
Speaker 2 (24:31):
I’m big fan of being in the field. It’s about user experience. It’s about science. It’s about quality of training. It’s about understanding that the specific problems. And so in each of our operations, even during COVID time, we visited except from one in Kenya where, because of COVID, we didn’t make it. We collaborate. So for example, in Ethiopia, we collaborated with Dr. ????, which is an Ethopian great scientist. And then you just learn a lot from, from such partners.
Speaker 3 (25:06):
And do you, so you mentioned already these field operations. Yeah. How do you measure basically how successful you are?
Speaker 2 (25:13):
You have two measures. One is about mosquitoes. So we catch mosquitoes. We don’t catch them to kill them, we catch them to count them – again inside the intervention area and then outside the intervention area to confirm the reduction rate of mosquito. And then, the more important, is to count malaria cases, if you reduce malaria cases.
Speaker 3 (25:32):
And what are the results?
Speaker 2 (25:34):
So in Ghana, this is the first time we did end-to-end trial. And then the results of mosquito reduction is amazing. As I said, it’s more than 60%. We think that the malaria results, because they collect them in lag.
Speaker 3 (25:47):
That sounds good. Like 60% seems to be a lot?
Speaker 2 (25:50):
60% is a lot because it says that every month you will call it Rzero. Rzero is the transmission rate is reduced by 60%. It’s actually linear in that area.
Speaker 1 (26:03):
What timeframe is that 60% reduction over, Arnon?
Speaker 2 (26:07):
It’s 100 days. So it’s less than four months. Now we start our most ambitious operation, which is about malaria elimination, really elimination to zero. And for that, we collaborate with the government of São Tomé and Príncipe. So, São Tomé and Príncipe is two islands, and is a sovereign country in West Africa. And because it’s islands, so it’s a closed system, yes, you don’t incoming mosquito and don’t go out. And then we want, in two years, to target the water bodies but not only target the water bodies also integrate other interventions in smart area together with artificial intelligence planning to understand also where to do what, and then to eliminate the disease. If that will happen, it opens up the opportunity to come to bigger countries and offer them malaria elimination. And malaria elimination, as we started, will save many people and will increase the economy. So people today understand that if you eliminate malaria from countries, the impact on the GDP on their economy will be like more than 10% in a few years now, it’s agriculture, it’s tourism, it’s education, it’s everything.
Speaker 3 (27:30):
Can you talk a little bit more about it? So obviously there is an imminent healthcare cost or healthcare impact of malaria, right? But you mentioned at the beginning that it drives poverty, it has economic implications.
Speaker 2 (27:42):
So the sad thing about malaria, and actually about many things in our world, is that it impact the poor people more than it impacts the rich people. Yes. So you have more malaria in poor villages from the good neighborhoods in the cities. You have malaria everywhere, but more in the village area. Or for example, in India, you have malaria more in some tribes in the mountains, rather than the whole population and then it attacks poor communities and then it’s, don’t let them go out of their poverty because it’s difficult to go forward.
Speaker 3 (28:20):
No, you cannot work when you get sick and so on. Yeah. So how did you get in touch with XPRIZE, did they reach out to you or did you apply through the program, how did it work?
Speaker 2 (28:30):
The competition every year we submitted a technical report about which algorithms we use, why we use them, what is the performance, everything. And then, each year, only a few of the companies continue. And the other based on that, so the judges looked at the techinical reports. And not only that, they also send judges to be with us in Ethopia so that they can really see what we do. The whole competition was very, the judging process was very rigorous and we shared with them our code. And then the last spot was not by the judges. It was by a jury, which is composed. They didn’t tell who are they? Who are the people that decide who will win the competition, who will be the second and third place they had chosen us and also the crowd. So we won the competition, but we also won the crowd category because many people voted for us.
Speaker 2 (29:33):
And I believe the reason is, I hope that because of two reasons. That I’m very happy that people care about this disease that happen elsewhere because we know that we know that people in Africa voted for us. We know it for sure, but we also know that people in Europe and the US and Israel voted for us even, they don’t experience malaria. And this is something we believe it’s a good sign for the world, countries really care about each other. And also I think because of our field, we were in the field, we have evidence. And this is very important to the judges. The competition was not only about technology, but about showing impact and about demonstrating future impact.
Speaker 1 (30:17):
What was it like when they announced you as the winner of the $3 million prize? Were you surprised? How did it feel?
Speaker 2 (30:24):
I was surprised. I told my friends, I’m sure I will be second. I was really, really, you know, kind of, I don’t know why I was so sure, but I was sure. And then when they told it, that we were the first, I just smiled like, like an idiot. And then my wife was in the other room and also a friend in the team and they came and just kissed me and hugged me and everything. And then I realised that something happy just happened.
Speaker 1 (30:57):
What difference will that make to you now, that large sum of money? What are you planning to do?
Speaker 2 (31:03):
First thing, we hope to use this money to attract more money. The money we will use it for one important thing, is the operation in São Tomé, we really hope to eliminate malaria in this country. This will be a revolution because never it happens in a country in central Africa, eliminated malaria. This is one thing. And second thing is to take our technology and artificial intelligence and protocols and biology understanding to just enlarge the team and do everything better and just take the product further.
Speaker 1 (31:39):
What’s happening in terms of more widespread adoption across Africa, are you hoping that one day this will be across the whole of Africa or is there, is that a challenging thing to scale to that degree?
Speaker 2 (31:51):
So for us it is not challenging. Yes. It’s software, basically. It’s not very difficult to scale. So it’s about the Ministry of Health, yes. If countries in Africa will adopt the system, it will just happen. And by the way, if one country use it, they help not only to themselves, but also to the neighbouring countries because mosquitoes you know they don’t believe in boundaries. So yes, I really hope to see it across the continent, not only Africa, but also South America, where you have malaria and in India. We must do our best to eliminate this disease. I think it’s very strange that we’re, you know, in the 21st century and we still have such disasters happening. So people, you know, now we had the 18 month of a Corona and we know how difficult it is, so why we allow such disease to persist for decades or centuries or both. We must, must stop it.
Speaker 1 (32:53):
Yes, because most of the deaths are in children. Isn’t that right?
Speaker 2 (32:55):
Yes. Children under five is most of the deaths. And then also pregnant women.
Speaker 1 (33:02):
And you see varying estimates. What would you put the estimates of number of people per year affected by malaria?
Speaker 2 (33:08):
I don’t have like better estimate than The World Health Organization, which is about 400,000 people, and last year it grew like 15% or so because of COVID. So, because of COVID, the organisation did not have the chance to give people more bed nets. And also the health clinics were less available for people and suddenly it increased the malaria.
Speaker 3 (33:36):
So you’ve worked a lot in this field of malaria prevention now the last couple of years. Are there any other organisations that you would want to mention that work on different approaches maybe tackling the same problem?
Speaker 2 (33:48):
If we will improve the available vaccine it will be amazing and some teams try to do so. Some tried to do so based on MRA technology and some try to just take the existing vaccine and with few modifications just enhance its capability. And other people try to do so with engineering mosquitoes, so they want to put genes in the mosquito that will, the mosquito itself will have a drug against malaria. And then the mosquito will not be infectious. This is very a innovative approach. If it will happen, it will be first time in history where humanity just take species from nature and just replace it in other species with different genes. This is interesting efforts that happened, but it’s still people that try to understand how to do it in terms of technology and also the safety of this method. And then recently there’s new methods of how to test the safety of such methods.
Speaker 3 (34:56):
If people want to support you, what can they do?
Speaker 2 (34:59):
I don’t want people to support us. I want people to support large malaria NGOs. And so, for example, Malaria No More and Only Nets are two good NGOs that really save many, many people. If you buy, for example, 10 bed nets, it costs $40 and potentially save life. So why not?
Speaker 1 (35:23):
And where can people find out more about your work and about Zzapp Malaria?
Speaker 2 (35:28):
Our site is Zzappmalaria.com.
Speaker 1 (35:32):
And that I’m afraid brings today’s really fascinating conversation to a close. First of all, Arnon thank you so much for joining us. It’s been an absolute pleasure having you here and thank you also to my cohost Phillip Diesinger for his excellent questions. And of course, to you for listening. Do check out the other XPRIZE episode on our podcast website@datascienceconversations.com. And if you did enjoy the show, then please do leave us a review on your podcasting platform. And we look forward to having you with us on the next episode. Thank you very much.
