Billy Rose

We trusted the- Well, you must feel good about the data. Exactly. Then the data though, we go to our actuarial team and we give it to our data scientist. Okay. Then he builds out a risk model and then we'd run it through a Monte Carlo simulation, which goes back to some of those classes that we really didn't always go to it. Did you go to Iowa State? For a little bit. Yeah. I did. Didn't we all.

Yes. So what we do is we run it through this model, a Monte Carlo simulation that creates the standard deviation and the mean running at over 10,000 iterations. So we get a really good idea as to how many times this will work or not work. Yeah.

Yes. So what we do is we run it through this model, a Monte Carlo simulation that creates the standard deviation and the mean running at over 10,000 iterations. So we get a really good idea as to how many times this will work or not work. Yeah.

Yes. So what we do is we run it through this model, a Monte Carlo simulation that creates the standard deviation and the mean running at over 10,000 iterations. So we get a really good idea as to how many times this will work or not work. Yeah.

We've modeled. We're going to be paying. Oh, yeah. There's so many factors out of our control. Yeah. And that's where we work with our reinsurance partners. Okay.

We've modeled. We're going to be paying. Oh, yeah. There's so many factors out of our control. Yeah. And that's where we work with our reinsurance partners. Okay.

We've modeled. We're going to be paying. Oh, yeah. There's so many factors out of our control. Yeah. And that's where we work with our reinsurance partners. Okay.

Yeah, it is. And at the same time, we're not looking to make home runs. We're very happy with a smaller margin so that we could keep the cost of that performance guarantee embedded into that package reasonable. Okay? So what do you call this? We're calling it the Yield Optimizer Program today.

Yeah, it is. And at the same time, we're not looking to make home runs. We're very happy with a smaller margin so that we could keep the cost of that performance guarantee embedded into that package reasonable. Okay? So what do you call this? We're calling it the Yield Optimizer Program today.

Yeah, it is. And at the same time, we're not looking to make home runs. We're very happy with a smaller margin so that we could keep the cost of that performance guarantee embedded into that package reasonable. Okay? So what do you call this? We're calling it the Yield Optimizer Program today.

And so we're working with two agribusinesses that are out there selling it through their distribution networks. We've had great success so far. Predominantly, it's in the Illinois and surrounding state area. and we do have a limited capacity going back to reinsurance capacity. But we have a lot for this first year. So we'd like to write about up to a million acres.

And so we're working with two agribusinesses that are out there selling it through their distribution networks. We've had great success so far. Predominantly, it's in the Illinois and surrounding state area. and we do have a limited capacity going back to reinsurance capacity. But we have a lot for this first year. So we'd like to write about up to a million acres.

And so we're working with two agribusinesses that are out there selling it through their distribution networks. We've had great success so far. Predominantly, it's in the Illinois and surrounding state area. and we do have a limited capacity going back to reinsurance capacity. But we have a lot for this first year. So we'd like to write about up to a million acres.

And again, we're really excited then. We're going to have four check block fields per farmer, and all that data is going to come back in, and that adds to our data flywheel effect, right? So we'll be able to take that Monte Carlo model and make it even a lot better. Keep learning. Yeah.

And again, we're really excited then. We're going to have four check block fields per farmer, and all that data is going to come back in, and that adds to our data flywheel effect, right? So we'll be able to take that Monte Carlo model and make it even a lot better. Keep learning. Yeah.

And again, we're really excited then. We're going to have four check block fields per farmer, and all that data is going to come back in, and that adds to our data flywheel effect, right? So we'll be able to take that Monte Carlo model and make it even a lot better. Keep learning. Yeah.

You do. And we look at two different data sets. We look at your crop insurance data sets, and then we take the as-applied data. And we have a specialized team that cleans up the as-applied data. As you know, a lot of combines are not calibrated. There's a lot of glitches in some of the software. Some guys don't turn it on. But that's part of our responsibility is we want to help you get –

You do. And we look at two different data sets. We look at your crop insurance data sets, and then we take the as-applied data. And we have a specialized team that cleans up the as-applied data. As you know, a lot of combines are not calibrated. There's a lot of glitches in some of the software. Some guys don't turn it on. But that's part of our responsibility is we want to help you get –

You do. And we look at two different data sets. We look at your crop insurance data sets, and then we take the as-applied data. And we have a specialized team that cleans up the as-applied data. As you know, a lot of combines are not calibrated. There's a lot of glitches in some of the software. Some guys don't turn it on. But that's part of our responsibility is we want to help you get –

data that you can trust.