944: Unleashing MATH to make better decisions in your business w/ Darren Tapp

WEBVTT

00:00:00.119 --> 00:00:01.082
Hey, what is up?

00:00:01.082 --> 00:00:04.371
Welcome to this episode of the Wantrepreneur to Entrepreneur podcast.

00:00:04.371 --> 00:00:12.648
As always, I'm your host, Brian Lofermento, and, being from Boston, I can confidently say that our guest today is wicked smart.

00:00:12.648 --> 00:00:17.905
This is a fellow New Englander who's doing incredible things in the world of numbers.

00:00:17.905 --> 00:00:36.048
Yes, we throw the word data around so much in business and entrepreneurship and when we talk about revenue and KPIs, but today's guest really applies such and not only academic but practical use of data and numbers and how we can tangibly use it for our own advantage in business growth.

00:00:36.048 --> 00:00:37.667
So let me tell you all about today's guest.

00:00:37.667 --> 00:00:39.305
His name is Darren Tapp.

00:00:39.619 --> 00:00:43.079
Darren earned a PhD in mathematics from Purdue University.

00:00:43.079 --> 00:00:53.524
His career has been in and out of academia, but currently he's focusing on industry and is interested in solving problems that face your small and medium-sized businesses.

00:00:53.524 --> 00:00:58.844
He provides business intelligence, data analytics and logistical solutions.

00:00:58.844 --> 00:01:07.010
He helps to advance companies using sound mathematical and statistical models, which I'm so excited to get into here in today's episode.

00:01:07.010 --> 00:01:18.087
He also helps existing teams incorporate better models and statistics into their operations, their monthly check-ins, their reports all of that so we can start making the right decisions and start actually growing.

00:01:18.087 --> 00:01:21.489
We're all going to learn a lot from today's guest, so I'm not going to say anything else.

00:01:21.819 --> 00:01:24.328
Let's dive straight into my interview with Darren Tapp.

00:01:24.328 --> 00:01:30.728
All right, Darren, I'm so excited that you're here with us today.

00:01:30.728 --> 00:01:31.590
First things first.

00:01:31.590 --> 00:01:33.504
Welcome to the show, Thank you.

00:01:33.504 --> 00:01:34.646
Thank you, Heck.

00:01:34.646 --> 00:01:43.022
Yes, so obviously we know that we always hear these big words today and you've got a lot to live up to, because I know that you've got so many valuable insights here.

00:01:43.022 --> 00:01:46.772
But before we get to the good stuff, Darren, take us beyond the bio.

00:01:46.772 --> 00:01:47.415
Who's Darren?

00:01:47.415 --> 00:01:51.323
How'd you start doing all these amazing things and applying it all to business?

00:01:51.805 --> 00:02:04.552
Well, actually I had a contact who is CEO of a debt collections agency and he brought me on and I needed a job.

00:02:04.552 --> 00:02:09.004
He's like well, I had this database and you'll need to know sequel.

00:02:09.004 --> 00:02:10.829
So I said I'll learn sequel.

00:02:10.829 --> 00:02:12.841
And he said, okay, start learn sequel.

00:02:12.841 --> 00:02:15.046
You start January 1st or something like that.

00:02:15.889 --> 00:02:21.229
And so I started to watch sequel videos on YouTube and I would fall asleep to them.

00:02:21.229 --> 00:02:23.804
So I'd have to watch them the next day and fall asleep again.

00:02:23.804 --> 00:02:29.907
So it's a very, very reliable way to fall asleep, I guess, if you want to learn SQL.

00:02:29.907 --> 00:02:40.405
But I learned it and and then I was embedded in their team that did a lot of analytics through their database.

00:02:40.405 --> 00:02:44.068
The team had to manage their database and it was huge.

00:02:44.068 --> 00:02:47.983
I consider it kind of a medium sized company.

00:02:47.983 --> 00:03:04.889
They had locations in Ohio and New Hampshire, and so I learned it real quick that I came with a different perspective from the mathematics background, and so I think that really fit in really well with the existing team.

00:03:04.889 --> 00:03:16.606
So that's how I ended up with doing the data analytics, but of course that wouldn't have been possible if I hadn't had the strong mathematical background to start with.

00:03:17.528 --> 00:03:19.052
Yeah, I love that overview, Darren.

00:03:19.052 --> 00:03:22.137
The question is then can we learn if we just fall asleep to that material?

00:03:22.137 --> 00:03:23.080
I've always wondered that.

00:03:23.860 --> 00:03:28.325
I think so there's a lot of overlap with set theory.

00:03:28.325 --> 00:03:33.570
I think that's kind of why I was falling asleep and probably the video I picked was maybe a more monotone voice.

00:03:33.570 --> 00:03:37.776
But I think if you just keep watching it you will learn.

00:03:37.776 --> 00:03:45.581
Yes, I mean it's yeah, so it's called the standard query query language.

00:03:45.581 --> 00:03:46.689
It's actually not a programming language, it's just.

00:03:46.689 --> 00:03:47.872
It's just kind of so.

00:03:47.872 --> 00:03:49.655
It's not as involved as other things.

00:03:49.655 --> 00:04:01.372
You might learn yeah and um, and some of my computer science friends say, since I had so much set theory, I do very well with like this, the sequel I'll pick up very quickly yeah I love it here on the show.

00:04:01.393 --> 00:04:08.543
it's something we talk about frequently is how these skills from our backgrounds they easily transpose into the thing and extrapolate into the things that we're doing today.

00:04:08.543 --> 00:04:23.327
I've got to be careful with my math terms with you here, but I will say we love that extrapolation of skills into all these different things because you obviously now in the business world you help businesses make sense of these complex data sets, and we live in a very data oriented world.

00:04:23.327 --> 00:04:27.665
We've got more data and numbers at our fingertips than probably any time in history.

00:04:27.665 --> 00:04:32.365
So, Darren, where was it, along the way that you, working in and out of academia, you said you know what?

00:04:32.365 --> 00:04:34.992
I've got a big value add for businesses.

00:04:34.992 --> 00:04:39.839
Not only can I help them with that, but you want to do it on your own accord, with your own business.

00:04:39.839 --> 00:04:41.302
Talk to us about that transition.

00:04:41.843 --> 00:04:45.952
Well, I guess it was a very specific problem.

00:04:45.952 --> 00:04:53.862
So Jason pulled me into his office and said hey, we're collecting on this debt and we have.

00:04:53.862 --> 00:04:58.192
You know, we pay money for the credit rating of all the people that owe money.

00:04:58.192 --> 00:05:24.759
And he said that maybe, if we do like a double variable extrapolation, where the first variable is a credit rating but the second variable is the time the debt has been inactive, and so I looked at both those variables and, sure enough, there was a correlation.

00:05:24.759 --> 00:05:30.564
So, you know, the more recent a debt, the more likely they were to collect on it.

00:05:30.564 --> 00:05:39.225
And so what I did is I did all the math stuff, the chi-square fits and all that, and worried about the variance and things like that.

00:05:39.980 --> 00:05:46.134
I ran some simulations and modeled it and came up with a new metric instead of the credit rating.

00:05:46.134 --> 00:05:56.548
It was mainly based on the credit rating, but it was just tweaked a little bit based on how old the debt was and on my different data sets.

00:05:56.548 --> 00:06:03.379
It did like 0.9% better at predicting if they would collect on a debt.

00:06:03.379 --> 00:06:11.269
And then I got thinking about that 0.9%, when you're collecting on a lot of debt, that's actually a lot of money, and so that's up.

00:06:11.269 --> 00:06:19.961
I mean, I was always very happy with that job but I was like, wow, if I, if I spin off by myself this, like this, that's a lot to collect.

00:06:19.961 --> 00:06:31.466
On right, I was only building hourly back then so but but yeah, those hours really probably I imagine they really paid off for the business.

00:06:32.127 --> 00:06:36.886
Yeah, and I think to that point, it really shows the value add when we pay attention to these numbers.

00:06:36.886 --> 00:06:37.548
I love that.

00:06:37.548 --> 00:06:48.127
Less than one percent when you multiply it by a lot of money, that is huge value add, and and obviously I'm just going to take this one quick second to interject to listeners that is huge value add and obviously I'm just going to take this one quick second to interject to listeners that I think that's important, darren.

00:06:48.127 --> 00:06:51.406
The value of your work is not from the mere hours that you work for a client.

00:06:51.406 --> 00:06:55.507
It is the value that you bring to them, so I think that's such an important entrepreneurial lesson.

00:06:55.927 --> 00:07:00.242
Let's talk about the data, though, because you're giving this one example, which we love tangible examples.

00:07:00.242 --> 00:07:06.065
Here on your website, you have some real examples of projects and things that you're working on with real life businesses.

00:07:06.065 --> 00:07:19.074
Talk to us about some of those data sets, because, obviously, on a really enterprise level, we can think about the millions, probably billions, of transactions that your visas, your stripe, is a tool that a lot of entrepreneurs and listeners are familiar with.

00:07:19.074 --> 00:07:21.216
We're familiar with those huge data sets.

00:07:21.216 --> 00:07:26.261
What are we looking at on a more micro level as far as small and medium-sized businesses?

00:07:27.622 --> 00:07:37.129
Well, medium-sized businesses have employees and you want to be able to understand how employees are doing.

00:07:37.129 --> 00:08:14.202
Especially once you get to the medium size, it's kind of hard to keep track of everybody, and you want to also be objective in how you assess your employees, and so if you have a database that's keeping track of what your employees are doing, and when and how, and the results of such, then you can come up with a report that's based on hard numbers and not just based on, oh, the manager likes you, and that can be used hard numbers and not just based on oh, the manager likes you, and that that that can be used at least I've had companies that want to use that to actually make the employees they have better.

00:08:14.202 --> 00:08:30.365
Of course, you could identify problems, employees that you might need to let go of, but the main goal is to get the most out of the employees you have, so so that that's an example of when you have all this data, what you might want to do with it.

00:08:32.494 --> 00:08:47.892
Yeah, darren, I want to ask you this because I'm a big believer, and there's that classic quote that we always hear in business of what gets measured, gets managed, and so, obviously, getting the right data, paying attention to the right data, collecting it when I mean this example of employee productivity, for example that's one thing.

00:08:47.892 --> 00:09:01.197
How can we, as business owners, as entrepreneurs, make sure that we're collecting data in a way that makes it useful, so that we actually have business intelligence, as opposed to a bunch of spreadsheets, a bunch of automations that we hook up in many different ways?

00:09:01.979 --> 00:09:05.053
Well, yeah, so what I do is I make those spreadsheets.

00:09:05.053 --> 00:09:05.738
I do that automation.

00:09:05.738 --> 00:09:18.587
So if they're not the right spreadsheet or something, you need to go in there and change the query.

00:09:18.587 --> 00:09:19.190
That's done.

00:09:19.190 --> 00:09:27.909
You might have to like, basically, you want to record everything you possibly can and then after the fact you'll figure out what you need.

00:09:27.909 --> 00:09:30.808
Usually you don't record exactly what you need.

00:09:30.808 --> 00:09:32.224
You have to kind of calculate.

00:09:32.224 --> 00:09:41.510
Based on the raw data, you might calculate whether here's your percentage, here's the percentage that the employees is converting, or something like that.

00:09:41.510 --> 00:09:49.360
So you need to.

00:09:49.360 --> 00:09:53.669
I think you should go back and review those spreadsheets you get and think about how you need them tweaked and all that.

00:09:53.669 --> 00:09:58.311
And if they do need to be tweaked, as long as the data is in the database, you can do that.

00:09:59.254 --> 00:10:09.341
Yeah, but I think that reveals part of your secret sauce, darren, with your mathematical background, about modeling of, you can see things beyond just the numbers, beyond just the spreadsheets that are looking in front of us.

00:10:09.341 --> 00:10:18.610
You've already used one of my favorite terms, which is extrapolate, which is the, the, what's the word that I want to say when things are correlated.

00:10:18.971 --> 00:10:21.085
I want to talk about correlation versus causation.

00:10:21.105 --> 00:10:23.331
That's where my brain is going, I want to say linear regression.

00:10:28.360 --> 00:10:29.783
So let's talk about correlation versus causation, because, for where my brain is going, I wanted to say linear regression.

00:10:29.783 --> 00:10:33.643
So let's talk about correlation versus causation, because for a lot of people without a mathematical background, this is something that can easily be messed up.

00:10:33.643 --> 00:10:35.929
I remember the first ever econometrics class that I took in college.

00:10:35.929 --> 00:10:45.969
Our professor had us look at the correlation between the number of sheep in Scotland and ice cream sales in New York City and of course, it had a high R squared value.

00:10:45.969 --> 00:10:47.451
It looked like it was highly correlated.

00:10:47.451 --> 00:10:50.162
Of course it was not causation in effect.

00:10:50.162 --> 00:10:57.096
So, darren, without going into a full on dissertation, but knowing that we're being listened to by entrepreneurs around the world, what is that difference?

00:10:57.096 --> 00:11:03.126
What's the important context for us to understand about correlation versus causation, and how does it play out in real life?

00:11:03.126 --> 00:11:03.768
Data sets?

00:11:04.509 --> 00:11:07.693
Well, correlation just means two things are related.

00:11:07.693 --> 00:11:10.563
When one goes up, one goes down, or vice versa.

00:11:10.563 --> 00:11:11.586
One goes up, the other goes up.

00:11:11.586 --> 00:11:13.192
That's a positive correlation.

00:11:13.192 --> 00:11:20.777
So the example I'm familiar with is drownings and ice cream sales.

00:11:20.777 --> 00:11:21.700
Those are correlated.

00:11:21.700 --> 00:11:27.232
You get more drownings when there's more ice cream sales and that is that's a correlation.

00:11:27.232 --> 00:11:31.966
But it's not that ice cream sales cause drowning or drowning causes ice cream sales.

00:11:31.966 --> 00:11:34.682
It's that there's an outside factor.

00:11:34.682 --> 00:11:41.471
When it's hot out there's, they sell more ice cream, and when it's hot out, more people swim and there's more chance of drowning.

00:11:41.471 --> 00:11:43.158
So outside factor.

00:11:43.177 --> 00:11:49.615
There's an another example oh, this was in the literature of a correlation.

00:11:49.615 --> 00:12:06.052
So they they found a correlation where children who slept with the light on didn't see as well, and the the original paper said they didn't know a causal link but just to be safe, turn the lights off before the kids go to sleep.

00:12:06.052 --> 00:12:16.429
And then later they learned that parents that are nearsighted are more likely to leave the light on and parents that are nearsighted are more likely to have children.

00:12:16.429 --> 00:12:18.933
Because it's genetic they can't see as well.

00:12:18.933 --> 00:12:23.660
So there that's another example of things being correlated, but not causal.

00:12:24.022 --> 00:12:27.032
Causal and the example I was doing with the debt collection.

00:12:27.032 --> 00:12:32.442
I don't think it really mattered if it was a causal relation or not, because you were just trying to pick.

00:12:32.442 --> 00:12:32.965
You didn't really.

00:12:32.965 --> 00:12:34.908
You your your.

00:12:34.908 --> 00:12:45.448
Your choice to go to collect on particular debt didn't didn't really affect the the outcome at all.

00:12:45.448 --> 00:12:59.035
So so just just knowing there's a correlation, it didn't have to be causal for it to be valuable for the company and and that that's that's a whole hard thing to predict it or that's a like that's a whole.

00:12:59.035 --> 00:13:03.208
You can first prove there's a correlation and can first prove there's a correlation and then to prove there's a causation there's.

00:13:03.208 --> 00:13:06.996
That's more you have to do yeah, makes sense.

00:13:07.297 --> 00:13:07.837
I'm loving this.

00:13:07.837 --> 00:13:15.097
As a numbers geek myself, darren, I love these insights, especially because I want to piggyback off of one of your really tangible real life examples.

00:13:15.097 --> 00:13:15.259
It's.

00:13:15.259 --> 00:13:16.544
It's right there on your website.

00:13:16.544 --> 00:13:18.129
People can go to your website listeners.

00:13:18.149 --> 00:13:21.380
We're going to talk about darren's website at the end of today's episode, but prior projects.

00:13:21.380 --> 00:13:26.674
I think it's so cool and you've given us the example of the employee performance here in our conversation today.

00:13:26.674 --> 00:13:35.427
I want to ask you this question because it's fun talking to a numbers person like you, where obviously, business is a balance of the personal stuff.

00:13:35.427 --> 00:13:44.815
We're dealing with real life humans, no matter what our business is, but also the data, the numbers that drive business growth, that drive productivity, that drive so many things we do.

00:13:45.135 --> 00:13:53.312
We have a lot of guests come on and talk about how to manage teams, how to build a corporate culture, but, darren, you take that other approach of hey, here's the facts.

00:13:53.312 --> 00:13:58.153
Let's first and foremost operate from the facts so we can make wise and strategic decisions.

00:13:58.153 --> 00:14:04.110
Being a numbers person, where is your view on how we integrate these successfully into our business?

00:14:04.110 --> 00:14:06.576
So, let's piggyback off of the employee productivity.

00:14:06.576 --> 00:14:14.129
How do I, as a business owner, make sure that my employees, my team members aren't thinking man, they're just tracking everything.

00:14:14.129 --> 00:14:16.736
They're going to use these numbers to get on my case about things.

00:14:16.736 --> 00:14:20.716
How can we make sure we implement it in a way that bolsters our performance?

00:14:21.865 --> 00:14:22.206
case about things.

00:14:22.206 --> 00:14:24.051
How can we make sure we implement it in a way that bolsters our performance?

00:14:24.051 --> 00:14:25.133
Well, at least the manager I was working with.

00:14:25.133 --> 00:14:36.851
Their intention was to review it every month, so, uh, so that you know every monthly is not like, oh, you're on your case all the time and that way you could, uh, the employee can kind of predict how they're doing.

00:14:36.851 --> 00:14:37.913
Uh, the.

00:14:38.014 --> 00:14:41.732
The hope is that they would, that the that would look.

00:14:41.732 --> 00:14:48.856
One check with the report card in one month would say, hey, you might need to improve on this metric for next time.

00:14:48.856 --> 00:15:01.475
And the hope was they actually would improve and so, instead of actually being on their case, you could be just like, oh great, look at that, wonderful, yeah, and so that's one way to make it feel like that.

00:15:01.475 --> 00:15:08.312
But did, but, yeah, so, so, but it's, it's the approach to be a collaborative.

00:15:08.312 --> 00:15:16.667
When you're dealing with actual hard data, with how the employees doing, it is when, when somebody gets hired, that's it's incident.

00:15:16.667 --> 00:15:27.461
It should be a collaborative relationship, so just pointing out how the employee is doing should be good.

00:15:27.461 --> 00:15:30.985
Another thing is, I would do every one of those in private.

00:15:30.985 --> 00:15:44.155
I wouldn't tell one person that they didn't do as well or did better than the other, and yeah, yeah.

00:15:44.416 --> 00:15:46.817
Two things I think it's really important to call out for listeners here.

00:15:46.817 --> 00:15:49.880
One, darren, you just revealed frequency matters of.

00:15:49.880 --> 00:15:52.261
If you know, you and I are meeting once a month.

00:15:52.261 --> 00:15:58.448
That is a check-in and it genuinely can be that supportive environment.

00:15:58.448 --> 00:15:59.071
So I love that insight.

00:15:59.071 --> 00:15:59.913
And then the second is collaborative.

00:15:59.913 --> 00:16:07.393
That's such an important thing to bring up in this conversation is that all of our metrics, all of the teams that we're all building to grow our businesses, it should all be collaborative.

00:16:07.393 --> 00:16:08.475
We're all in this together.

00:16:08.605 --> 00:16:16.769
So one of our founding principles I say it so frequently here on the show is a rising tide lifts all boats and I love how it shows up even in your work, darren, because it's so important.

00:16:16.769 --> 00:16:24.921
And I want to ask you this question because, looking at your work, it just seems like you obviously have a ton of different skills and all different types of data sets.

00:16:24.921 --> 00:16:35.775
The way that you approach this, the visualizing of the problems that businesses are facing with the data that they have in front of them, how do you begin to assess the overall landscape?

00:16:35.775 --> 00:16:38.065
So one example has been employee productivity.

00:16:38.065 --> 00:16:42.456
When you walk into a business, how is it that you find that value?

00:16:42.456 --> 00:16:43.177
Where is it?

00:16:43.177 --> 00:16:44.571
Do you look at sales?

00:16:44.571 --> 00:16:46.091
Do you look at operations?

00:16:46.091 --> 00:16:50.596
What is it that makes you say hey, you guys, there's some answers in your numbers here.

00:16:50.596 --> 00:16:52.686
Let's poke and prod here, I'm guessing.

00:16:52.686 --> 00:16:56.876
I'm asking, darren, where are you poking and prodding to start going down this path?

00:16:57.946 --> 00:16:59.854
Well, it's kind of a general question you're asking.

00:16:59.854 --> 00:17:27.574
It would depend on the actual details of the business, but basically you would want to first they actually make a sale, but then that's going to be influenced by other things.

00:17:27.574 --> 00:17:46.835
Like an employee might be working at 3 pm on a Tuesday and that's not primetime shopping, and then another employee might be working on you know, it's 5 pm on a Saturday and people love to go out and shop then.

00:17:46.835 --> 00:18:03.171
So you would want to somehow account for these differences in times and so you could kind of actually compare oh you're doing, even though you didn't sell as much on Tuesday, you're doing very well because the person on Saturday had an advantage.

00:18:03.171 --> 00:18:26.278
So you would want to be able to quantify kind of how each employee should do, based on they're not all in the same environment, and actually try to take that out, take that noise out of your numbers.

00:18:27.721 --> 00:18:37.257
Yeah, and I want to go back to because when we're talking about using our numbers in this way, it begs the question for a lot of business owners of hearing your skillset SQL, python.

00:18:37.257 --> 00:18:39.089
Obviously you're working a lot in Excel.

00:18:39.089 --> 00:18:45.195
There's so many different tools that you're using, darren, for your clients and for business owners in any way who want to tap into the data.

00:18:45.195 --> 00:18:47.666
What does this actual workflow look like?

00:18:47.666 --> 00:18:53.755
Is this a one-time thing that you go in with these businesses and you set systems up that you generate these reports for them?

00:18:53.755 --> 00:19:02.633
Or how can we embed this into our ongoing maintenance and check-ins of our own business metrics so that we can continue to stay on top of this stuff?

00:19:03.675 --> 00:19:06.727
So, yeah, I mean I could do a one-off problem.

00:19:06.727 --> 00:19:14.518
Some businesses need data analytics done and they just need that done, and then, um, and then that's it.

00:19:14.518 --> 00:19:17.527
Uh, but, uh, what.

00:19:17.527 --> 00:19:29.404
What I'm used to is uh, uh, being being basically asked a question every week or so, and then I would go and just uh, you know, go through the database and come up with the answer.

00:19:29.404 --> 00:19:31.871
Question, uh, and, and, and.

00:19:31.871 --> 00:19:34.517
Just just that process you get to learn.

00:19:34.517 --> 00:19:39.816
Basically, every business database is going to be a little bit different.

00:19:39.816 --> 00:19:55.178
Sometimes it's not documented the best, and so every time you answer a question you get more and more familiar with the database, and then that starts a relationship where I can become more and more valuable as time goes on.

00:19:56.365 --> 00:19:58.411
Yeah, and that's a very important distinction.

00:19:58.411 --> 00:20:02.971
One of my topics that I'm so excited to talk to you about here today is that essence of time.

00:20:02.971 --> 00:20:16.577
It's something that we all look at, and I think back to business school, where all of our professors tell us to have a five-year plan, a 10-year plan, and then I can't help but think about 2020, and all of those plans, no matter how far out you were looking, all got thrown out the window.

00:20:16.577 --> 00:20:24.570
Obviously, the world changed in a lot of ways in 2020.

00:20:24.590 --> 00:20:32.892
So, darren, with time being a factor, a variable in all of the data sets that we look at, especially when we talk about future forecasting and modeling, with your mathematical hat on, what is your attitude towards time?

00:20:32.892 --> 00:20:34.694
Obviously, things are always changing.

00:20:34.694 --> 00:20:36.096
Technology's changing.

00:20:36.096 --> 00:20:38.380
What is a valuable data set for us?

00:20:38.380 --> 00:20:46.420
Whether we're looking backwards, of saying, hey, let's look at six months of employee data, let's look at six months of sales data, is it a large window of time?

00:20:46.420 --> 00:20:47.585
Is it a smaller window of time?

00:20:47.585 --> 00:20:49.410
How do we extrapolate that into the future?

00:20:49.410 --> 00:20:56.506
I'd love to get inside your mind there into the future.

00:20:56.526 --> 00:20:59.009
I'd love to get inside your mind there.

00:20:59.009 --> 00:21:15.759
Yeah, so I was just in a lunch meeting with some colleagues and there was a successful trading strategy that was being employed in the past, but then I think word about this trading strategy got out or something, or something happened in the market and all of a sudden the trading strategy didn't work.

00:21:15.759 --> 00:21:27.181
So so that's an example where there's one time period where certain conditions were met and somehow things changed after a certain date.

00:21:27.181 --> 00:21:43.936
So when you are, when your question is time about time, you should you should pick a time period where you don't think there's been any major changes in in your, in your business model.

00:21:43.936 --> 00:21:47.368
So you mentioned the COVID situation.

00:21:47.449 --> 00:22:16.449
So now if you're doing a, if you're looking back on like 10 or 20 years of, let's say, 20 years of data for your business, you might actually just take out that code, like the two or three years of code, and just and and look at that separately and see if it differs qualitatively from all the others and if so, you would throw that out In statistics.

00:22:16.449 --> 00:22:17.090
That's called a.

00:22:17.090 --> 00:22:19.636
What's that called an outlier?

00:22:19.636 --> 00:22:23.505
You have sometimes, you have data, but sometimes there's this outlier.

00:22:23.505 --> 00:22:25.532
That's not going to be the general case.

00:22:25.532 --> 00:22:32.994
You know, in your retail you might sell a pair of pants, a shirt to somebody, but then somebody comes in and buys, you know, half the store.

00:22:32.994 --> 00:22:33.967
That's an outlier.

00:22:33.967 --> 00:22:41.449
You can't, you can't, your model can't really predict that you're going to have this outlier that happens in the future.

00:22:41.449 --> 00:22:45.738
So so that's that's how you pick your time period.

00:22:45.738 --> 00:22:54.807
You want a time period where it's generally the same and you would want to throw out any outliers, whether it's an outlier time period or outlier data point.

00:22:55.430 --> 00:23:06.292
Yeah, and the word, one word used earlier in our conversation is noise, obviously, and I think that for so many of us entrepreneurs acknowledging what is the noise, what are the outliers, what's the stuff, that isn't something that is actionable.

00:23:06.292 --> 00:23:14.415
It's funny for me, as I obviously get to have so many amazing conversations with great entrepreneurs, and a lot of listeners email in and they say, oh, can I do what this person did?

00:23:14.415 --> 00:23:15.758
Is it going to work for my business?

00:23:15.758 --> 00:23:23.671
And the reality is well, their circumstances, what's going on in their life in that time period and the way tech is radically different than the way that the world is now.

00:23:23.671 --> 00:23:25.395
So it may or may not be.

00:23:25.395 --> 00:23:27.186
Chances are it is not replicable.

00:23:27.186 --> 00:23:28.448
So I think that's really important.

00:23:28.788 --> 00:23:31.452
Darren, I always appreciate speaking of those conversations.

00:23:31.452 --> 00:23:41.316
I always love transitioning these conversations to talk not only as a subject matter expert, but entrepreneur to entrepreneur, because it's easy for someone to look at your business and think Darren's a numbers person.

00:23:41.316 --> 00:23:43.490
This is what he does, this is what he's amazing at.

00:23:43.490 --> 00:23:54.477
I want to get inside your mind as an entrepreneur, because you're not just in the data, you're not just in the numbers for your clients, you are also growing your own business and you've been at this for quite some time now.

00:23:54.477 --> 00:23:57.182
We love celebrating entrepreneurial longevity.

00:23:57.182 --> 00:24:01.994
Talk to us about the approach and how it feels for you that you're not just a practitioner.

00:24:01.994 --> 00:24:16.000
I know that you've been a professor in the past and there's so many things in the world of academia that you've done, but how is life different as a business owner, as an entrepreneur who's not just doing what you love, but you're also building a business and doing all the other stuff that comes with it?

00:24:18.388 --> 00:24:24.698
Well, it can be frustrating because the reward is inconsistent.

00:24:24.698 --> 00:24:32.337
Sometimes there's a big reward, sometimes there's not any reward, so that's a little frustrating with running your own business.

00:24:32.337 --> 00:24:38.241
So that's a little frustrating with running your own business, let's see.

00:24:38.241 --> 00:24:44.656
But I've been able to actually do my own projects, like you mentioned, the projects on the website.

00:24:44.656 --> 00:24:46.090
So I made a trading bot.

00:24:46.090 --> 00:25:03.153
I was able to implement that for just myself and it's a really interesting trading strategy and everything, and that turned out to help bridge the gap when a client wasn't around.

00:25:03.153 --> 00:25:09.286
So finding my own projects has been very helpful too.

00:25:09.286 --> 00:25:11.535
So that's one thing.

00:25:11.535 --> 00:25:17.952
Yeah, if, if you're going to see what you can do for yourself first and then, uh, then help other people as well.

00:25:18.453 --> 00:25:21.471
Yeah, I love that advice and it's such a real life example.

00:25:21.471 --> 00:25:28.363
It's something that I cherish as part of the entrepreneurial journey is playing around for for me, obviously, as a podcaster, I love new technologies.

00:25:28.363 --> 00:25:32.654
I love seeing different AI tools and what they can do with the transcripts of our episodes.

00:25:32.654 --> 00:25:35.871
It's fun to whether it ever sees the light of day, darren, or not.

00:25:35.871 --> 00:25:36.913
Truth be told, it's just.

00:25:36.913 --> 00:25:46.073
It's fun to play around in the playground and our businesses are an ongoing playground for us to continue growing, for us to continue upskilling and experimenting.

00:25:46.073 --> 00:25:47.174
So I really appreciate that.

00:25:47.174 --> 00:25:53.272
I also know that part of what you do is you obviously have tap root investments where you're the chief financial officer.

00:25:53.272 --> 00:25:58.165
Darren, talk to us about your interests externally, aside from just what you're doing with tap math.

00:25:58.926 --> 00:26:24.957
Well, yeah, so you know, part of part of just being alive is you want to make sure you're you're going to be able to handle any situation that happens, and so investing in property seems like something that is something that will pan out no matter what the financial situation turns out in the future.

00:26:24.957 --> 00:26:32.939
And so it's a little small company that owns a couple of commercial spaces and is renting them out.

00:26:32.939 --> 00:26:35.752
So that's kind of fun.

00:26:35.752 --> 00:26:42.230
We just I just worked with a guy that was helping me fix a ramp, so so it's.

00:26:42.230 --> 00:26:56.489
It's funny, being an entrepreneur, like I can't do all the not everything I do is the high level math stuff, but it's kind of fun to come back to earth and, just, you know, make sure the company has a ramp replaced so that they need.

00:26:57.191 --> 00:27:00.057
So yeah, and it's funny because that's the real stuff.

00:27:00.057 --> 00:27:05.506
Darren, I feel like a lot of podcasts and YouTube videos and especially entrepreneurial and business related books.

00:27:05.506 --> 00:27:13.737
They don't talk about these realities, which is why we're so appreciative to have you here on the show to talk to us about the different, the varied things, of even pulling these in.

00:27:13.737 --> 00:27:30.194
And I want to ask you this because, knowing that you've been a professor before and you've worked inside of academia and with students who are information sponges looking to learn all the things, I'm curious what about that part of your backstory and your background and your experiences plays into the way that you do business today?

00:27:30.194 --> 00:27:38.446
I'm curious if there's things that help you in your customer service, if you take some of those techniques and teaching others that you've implemented into your business practices.

00:27:39.249 --> 00:27:46.211
I think the fact that my background as a teacher does really help if I'm an embedded, if I'm embedded into a team that exists already.

00:27:46.211 --> 00:28:07.195
It seems like, you know, this word is overused, but there can be a synergy between bringing in some outside knowledge and to an already existing team, and so I think that just being a teacher helps me with those human interactions that people have to do.

00:28:07.195 --> 00:28:14.357
And then, let's see, I also think that it does help me train staff.

00:28:14.357 --> 00:28:18.932
Now, mostly it's informal, like oh, somebody needs to know something.

00:28:18.932 --> 00:28:26.609
Okay, like one of our research projects I did in academia is working with Nicole, and Nicole's like why do you need this simulation?

00:28:26.650 --> 00:28:32.741
Run five or 20 times, or how many ever times I asked him to run it and I told him about the statistics behind it, and so that was a teachable moment, so to speak.

00:28:32.741 --> 00:28:33.852
Or how many ever times I asked him to run it and I told him about the statistics behind it?

00:28:33.852 --> 00:28:36.657
And uh, so so there's, that was a teachable moment, so to speak.

00:28:36.657 --> 00:28:41.872
That was in academia, but that you could see how that would translate to uh, um, uh to uh.

00:28:41.872 --> 00:28:53.011
And then, when I was embedded in that team working on uh spreadsheets and such um, I was learning from the database-based people and they were learning from me.

00:28:53.132 --> 00:29:04.102
And the one example I did with that regression, the correlation that I don't believe was causal.

00:29:04.102 --> 00:29:23.471
I can't really say it's causal, but with the time of the debt, that correlation problem, that was something I felt like I was specially trained for, that the rest of the team couldn't do, and then when, after I did it, I could explain to the rest of the team why I thought it was a good thing.

00:29:23.471 --> 00:29:29.492
So it kind of brings in a different perspective which I think, like you say, a rising tide raises all boats.

00:29:29.573 --> 00:29:36.288
So I think, yeah, yeah, and speaking of the academic background, I do want to tap into cause.

00:29:36.288 --> 00:29:41.069
I found this so fascinating about your background, what you said about ASU, arizona state university.

00:29:41.069 --> 00:29:44.577
I think that that has clearly left such a big impact on you.

00:29:44.577 --> 00:29:58.926
I can see from the outside and say that because so much of your marketing language on your website, the way that your business shows up, you talk about solving those problems and I know that ASU is kind of also rooted in that way that problem solving.

00:29:58.926 --> 00:30:06.134
Talk about what makes ASU's approach different and how it left such an important mark on the way that you see the world and the way you operate.

00:30:06.805 --> 00:30:12.416
Yeah, so it just happened and it was weird.

00:30:12.416 --> 00:30:25.576
But like I went to Purdue and I think Purdue is a wonderful school and I based that on the math library being it always had everything I needed and and when my advisor and wonderful professors that were there as well.

00:30:25.576 --> 00:30:42.191
But when I, when I migrated to Arizona State University, it was kind of just a happy circumstance I was in industry and then industry said hey, darren, join a research team that we're working with, with ASU, that we're starting a partnership with ASU.

00:30:42.191 --> 00:30:45.453
And then ASU poached me a year or two later.

00:30:45.453 --> 00:31:05.435
So but yeah, so ASU as a university is built, they don't build their departments around subjects and in fact they're not even called departments, but they build basically what are departments around?

00:31:05.516 --> 00:31:06.759
Types of problems.

00:31:06.759 --> 00:31:16.352
So like I was in the automated decision department, I wasn't in the computer science department.

00:31:16.352 --> 00:31:21.574
There's actually a few departments that might be considered computer science.

00:31:21.574 --> 00:31:26.333
So I was in the decision, like the computer decision department.

00:31:26.333 --> 00:31:42.756
And so since they're developed then, since they're organized around types of problems, when you want to solve a problem you don't just like you want to solve even a physics problem, you don't necessarily need 20 physicists to do this.

00:31:42.805 --> 00:32:25.373
You might want to have three or four physicists, but then bring in a mathematician, you know, maybe an engineer, maybe, you know, bring in a kind of a breath of subjects and you you have a better chance of solving the problem because you know, with all the different ways of looking at it, if you get stuck in one part, maybe somebody in that breath that you brought in would be able to deal with that one part, and and I think that was that's a really great way of organizing a university and it it really it does have an impact on you when you uh, because I thought this is weird, this mathematician in this computer science team.

00:32:25.373 --> 00:32:37.353
But uh, it's not weird at all, it's like that's exactly what you would do, um, if you were interested in solving problems, not just uh, advancing knowledge.

00:32:38.154 --> 00:32:48.551
yeah, really well, I really appreciate those insights and I so appreciate the way that you articulate it because, like I said, I think your work exemplifies that approach and it's such a different way of thinking.

00:32:48.551 --> 00:32:51.473
So, with all of that in mind, darren, I always like to.

00:32:51.473 --> 00:32:58.869
This is a selfish way for me to end these episodes, because I truly have no idea which direction you're gonna take this question and you can go anywhere with it.

00:32:58.869 --> 00:33:12.541
And that is what's your one piece of advice, the one takeaway for listeners, knowing that we're being listened to by thousands of entrepreneurs and entrepreneurs in over 150 countries at all different stages in their business growth and you are one of us, darren.

00:33:12.541 --> 00:33:18.136
You are a fellow entrepreneur what's that one piece of advice that you hope they walk away from today's episode with?

00:33:19.724 --> 00:33:21.023
What's that one piece of advice that you hope they walk away from today's episode with?

00:33:21.023 --> 00:33:21.214
Okay.

00:33:21.214 --> 00:33:22.655
So this is very simple.

00:33:22.655 --> 00:33:37.028
But if you know your numbers, but specifically know your burn rate and your runway, so you should know all your numbers.

00:33:37.028 --> 00:33:45.944
But if you don't know any numbers, know how much money you're spending a month in your business and know how, how much time you have until you're out of money.

00:33:45.944 --> 00:33:47.087
That's what your runway is.

00:33:47.087 --> 00:33:53.731
So those two things are the one, two things you should know if you don't know anything yeah, I love that, darren.

00:33:53.751 --> 00:33:56.018
In over 900 episodes, you're the first one that.

00:33:56.085 --> 00:34:05.125
That's the clear takeaway and you said it's simple, but it is so boring, like a cliche or something everybody's like I don't know these things anyway no, that's incredible.

00:34:05.185 --> 00:34:05.949
I absolutely love that.

00:34:05.949 --> 00:34:08.735
It's because listeners hear me say this every single week.

00:34:08.735 --> 00:34:15.179
It's my favorite albert einstein quote and it's something that we so appreciate when our guests do it, which is if you want to impress someone, make it complicated.

00:34:15.179 --> 00:34:17.266
If you want to help someone, make it simple.

00:34:17.266 --> 00:34:21.255
And darren, you've done just that, while also challenging us to think differently.

00:34:21.255 --> 00:34:26.472
So I'm so excited for listeners to go down the Darren Rabbit Hole with TapMath.

00:34:26.472 --> 00:34:27.275
I think it's so cool.

00:34:27.275 --> 00:34:30.331
All the things you're doing, all the content that you're putting on your website.

00:34:30.331 --> 00:34:36.532
I love seeing those real life insights, the work that you're doing, and you do have a knack for making it digestible and simple.

00:34:36.532 --> 00:34:37.655
So huge kudos to you.

00:34:37.655 --> 00:34:40.360
With all of that said, drop those links on us.

00:34:40.360 --> 00:34:43.791
Where can listeners go to learn about all the awesome stuff that you're up to?

00:34:45.085 --> 00:34:53.994
Oh well, tapmathcom is where I do most of my business stuff, and then I have darrentapcom, which is about me personally.

00:34:53.994 --> 00:34:57.594
Those are the websites.

00:34:58.025 --> 00:34:59.385
Listeners, you already know the drill.

00:34:59.385 --> 00:35:06.230
We're making it as easy as possible for you to find darren and his business online, no matter where it is that you're tuning into today's episode.

00:35:06.230 --> 00:35:09.005
Scroll right on down and you'll find those links you can click right on through.

00:35:09.005 --> 00:35:12.311
His main business website is at tapmathcom.

00:35:12.311 --> 00:35:19.291
That's tap, t-a-p-p-p-p-mathcom, just like his last name that you see in the title of this episode.

00:35:19.291 --> 00:35:20.755
So, listeners, don't be shy.

00:35:20.755 --> 00:35:25.809
And, darren, on behalf of myself and all of our listeners around the world, thanks so much for coming on the show today.

00:35:25.809 --> 00:35:27.114
Thank you, brian.

00:35:27.114 --> 00:35:33.577
Hey, it's Brian here and thanks for tuning in to yet another episode of the Wantrepreneur to Entrepreneur podcast.

00:35:33.577 --> 00:35:37.614
If you haven't checked us out online, there's so much good stuff there.

00:35:37.614 --> 00:35:44.052
Check out the show's website and all the show notes that we talked about in today's episode at thewantrepreneurshowcom.

00:35:44.445 --> 00:35:46.833
And I just want to give a shout out to our amazing guests.

00:35:46.833 --> 00:35:55.592
There's a reason why we are ad free and have produced so many incredible episodes five days a week for you, and it's because our guests step up to the plate.

00:35:55.592 --> 00:35:57.652
These are not sponsored episodes.

00:35:57.652 --> 00:35:59.268
These are not infomercials.

00:35:59.268 --> 00:36:02.755
Our guests help us cover the costs of our productions.

00:36:02.755 --> 00:36:13.715
They so deeply believe in the power of getting their message out in front of you awesome entrepreneurs and entrepreneurs that they contribute to help us make these productions possible.

00:36:13.715 --> 00:36:22.193
So thank you to not only today's guests, but all of our guests in general, and I just want to invite you check out our website because you can send us a voicemail there.

00:36:22.193 --> 00:36:23.530
We also have live chat.

00:36:23.530 --> 00:36:28.152
If you want to interact directly with me, go to thewantrepreneurshowcom.

00:36:28.152 --> 00:36:29.556
Initiate a live chat.

00:36:29.556 --> 00:36:37.711
It's for real me and I'm excited because I'll see you, as always every Monday, wednesday, friday, saturday and Sunday here on the Wantreprene.