Growing profitability with data in the field.

Since human beings began growing crops in a field to establish communities, the mantra has always been “grow more”. Growing more means more food, more stability, and (of course) more money. That money means better equipment, more land, and a means to retire and let the next generation take over. However, one company is showing farmers how to increase profit margins through the use of data.

JC from Crop Tech Solutions in their test field showing how planting depth can aid or hinder the ability of the plant to absorb nutrients. When you lean up your inputs getting every last drop to count is crucial. *Photo taken the morning after heavy rain and 60mph winds

However, with the advent of technology the time honored tradition of growing more took an odd turn. Corn is an industry that measures success in bushels per acre. In chasing more bushels per acre more inputs are needed to push crops to new levels. Farmers may even go bankrupt trying to get a 20% increase in bushels just to better their neighbor or hit a projection.

The advent of technology has changed the paradigm in how crops are cultivated and how they can be grown. Keep in mind, people were still using livestock to plow fields as late as the 1950’s. Now they use ultra precise GPS to navigate a family farm they know like the back of their hands, all for more bushels per acre at harvest time.

John Deere – 1775NT 24 Row 30 Drawn Planter is an example of the level of sophisticated tech in agriculture farmers are pairing with data. This piece of equipment is a far cry from what they used on this ground 50-100 years ago.

With the quest for more bushels comes the additional costs and “inputs”. Inputs can be anything you put into a field to help it grow: water, fertilizer, herbicide, pesticide, and more are all inputs. With deep enough pockets you can fund any number of thousands of variables that go into a particular field. But are those inputs really helping you make more money?

Working Smarter not Harder

One company, Crop Tech Solutions, realized you can work smarter and not harder. As it turns out being too productive and chasing higher bushel counts can actually be detrimental to your bottom line. Its such a foreign idea let me write that again another way. You can make more money, from less bushels per acre.

JC Smith with Crop Tech Solutions showing the CAN team the difference planting depth can have on plant growth in a test field. *Photo taken the morning after heavy rain and 60mph winds

Seed companies want to sell more seeds, so more seeds means more profit…but for whom? The soil and field conditions will dictate how the corn grows in the field, not the seed count going in. The more you have to add to that field in terms of inputs the more money it will cost to grow it. Each input erodes your profit margin and if its a down year for corn pricing, you’re in the red pretty fast.

“Traditional” field across the road. Plants of different heights, brown spots, bald spots, smaller plants, tighter grouping, higher input levels. *Photo taken the morning after heavy rain and 60mph winds
An optimized field under Crop Tech Solutions watch. Solid green with no brown spots, low spots, or inconsistent growth. *Photo taken the morning after heavy rain and 60mph winds

So, somewhat counter intuitively, you can make more money farming with less bushels per acre. By using the data and the technology for precision planting you maximize the potential of the plants without competing for resources. Farming smarter, not harder, the plants can reach a greater potential without competing for resources.

Growing with CAN

Contemporary Analysis has been working with Crop Tech Solutions to get even more from their data. The more effective their data collection and prediction, the easier it is for their customers to see significant gains in profitability. Crop Tech Solutions has been able to help local farmers find Millions in efficiencies, and shows no signs of stopping any time soon.

Crop Tech delivers customized prescriptions for each field. Based on the data points from various aspects of farming. As they layer additional data to the process, the more they are able to predict the best combination of field characteristics and inputs. Their prescription helps crops grow to their fullest potential without wasting input dollars trying to push it along.

Example of the data visualization offered from Crop Tech Solutions. The heat map shows how the field was planted and prescribed growth for inputs. When input into precision planting equipment every individual plant has its optimal conditions for growth.

So how do you get more profit from LESS bushels per acre? It all comes down to how much you have to spend to grow the corn. To get 250 bushels per acre you have to purchase chemicals, fertilizer, fuel, and more. These inputs are often in significant quantities to “push” the field to that bushel target. Plants have to compete for resources so they are strained and don’t grow to full potential. Resources like water, sunlight, and root size can dramatically change the way your crops grow.

Working in inches over hundreds of acres can equate to hundreds of thousands of dollars in savings each year. *Photo taken the morning after heavy rain and 60mph winds

When you use the data to understand what the ground can carry, down to the inch in the field, you can optimize every row to get monster corn that isn’t struggling for limited resources. When the corn can grow to its full potential, you don’t have to spend thousands of dollars trying to push it along. The data takes the “gut feeling” out of farming.

Precision agriculture delivers results, but only if you know how to deploy it. You can have the best equipment in the world, but if you don’t set it up right you’re wasting money. The prescription delivered from the layered data points helps program seed planting equipment (for example) accurately. A section of your field may call for a 6 inch gap between plants while another segment, 20 feet away, may call for 1 1/2 inches between plants. The compulsion to “split the difference” and then “set it and forget it” could cost you hundreds of thousands of dollars in the long run. You’re literally betting the farm on how many inches apart you place crops in the field.

JC showing the guys from CAN how the planting types can change from row to row with precision agriculture. This test field shows how plants that are grouped closely together compete for resources. Others that are spaced too far apart aren’t using all the input resources and wasting money in the process. *Photo taken the morning after heavy rain and 60mph winds
Even the depth of the seed being planted can effect the yield per plant. The goal is to understand the variables and how to optimize them for each square food of growing space. *Photo taken the morning after heavy rain and 60mph winds

Very few farmers work on an all cash basis. Each year they take a loan from the bank to fund the operation. These loans can be in the hundreds of thousands or even millions of dollars. The less you can spend on inputs the less you need to borrow. The less you need to borrow, the less you have in interest payments. When you go to sell your crops the fluctuating prices mean the farmer who grew quality crops with lean inputs will see more profit. The farmer who grew to the seed company suggestions has a skinnier margin (if any) and could actually lose money growing corn in a bad year.

The red row is planted to the seed provider spec. The blue row is planted to the field and how it can grow corn most efficient. *Photo taken the morning after heavy rain and 60mph winds

The Payoff

At Contemporary Analysis we love working in what we call the “Steel toe industries”. These areas include, Agriculture, Construction, Manufacturing, Transportation, and Logistics. We carry over lessons learned from our non-steel toe clients and vice versa. The end result is a broad spectrum of options where others may only see one or two.

Our goal is to help companies make better data driven decisions at every turn. In this instance, its helping farmers remain profitable year over year. Because of the champions of data like Crop Tech Solutions we can help keep families and even entire communities thriving through data.

Overall we had a great visit with the guys from Crop Tech Solutions. They even gave us a private tour of the Sod House Museum which is one of their passion projects.

If you’d like to see how we could help you do more with less, contact us.

machine learning prediction

March Machine Learning Mayhem

Machine Learning and the NCAA Men’s Basketball Tournament Methodology

 <<This article is meant to be the technical document following the above article. Please read the following article before continuing.>>

“The past may not be the best predictor of the future, but it is really the only tool we have”

 
Before we delve into the “how” of the methodology, it is important to understand “what” we were going for: A set of characteristics that would indicate that a lower seed would win. We use machine learning to look through a large collection of characteristics and it finds a result set of characteristics that maximizes the number of lower seed wins while simultaneously minimizing lower seed losses. We then apply the result set as a filter to new games. The new games that make it through the filter are predicted as more likely to have the lower seed win. What we have achieved is a set of criteria that are most predictive of a lower seed winning.
 
This result set is fundamentally different than an approach trying to determine the results of all new games whereby an attempt is made to find result set that would apply to all new games. There is a level of complexity and ambiguity with a universal model which is another discussion entirely. By focusing in on one result set (lower seed win) we can get a result that is more predictive than attempting to predict all games.
 
This type of predictive result set has great applications in business. What is the combination of characteristics that best predict a repeat customer? What is the combination of characteristics that best predict a more profitable customer? What is the combination of characteristics that best predict an on time delivery? This is different from just trying to forecast a demand by using a demand signal combined with additional data to help forecast. Think of it as the difference between a stock picker that picks stocks most likely to rise vs. forecasting how far up or down a specific stock will go. The former is key for choosing stocks the later for rating stocks you already own.
 
One of the reasons we chose “lower seed wins” is that there is an opportunity in almost all games played in the NCAA tournament for there to be a data point. There are several games where identical seeds play. Most notably, the first four games do involve identical seeds and the final four can possibly have identical seeds. However, that still gives us roughly 60 or so games a year. The more data we have, the better predictions we get.
 
The second needed item is more characteristics. For our lower seed win we had >200 different characteristics for years 2012-2015. We used the difference between the characteristics of the two teams as the selection. We could have used the absolute characteristics for both teams as well. As the analysis is executed, if a characteristic is un-needed it is ignored. What the ML creates is a combination of characteristics. We call our tool, “Evolutionary Analysis”. It works by adjusting the combinations in an ever improving manner to get result. There is a little more in the logic that allows for other aspects of optimization, but the core of Evolutionary Analysis is finding a result set.
The result set was then used as a filter on 2016 to confirm that the result is predictive. It is possible that the result set from 2012-2015 doesn’t actually predict 2016 results. Our current result set as a filter on 2016 data had 47% underdog wins vs. the overall population. The historic average is 26% lower seed wins and randomly, the 47% underdog win result could happen about 3.4% of the time. Our current result is therefore highly probable as a predictive filter.
 
The last step in the process is to look at those filter criteria that have been chosen and to check to see if they are believable. For example, one of the criteria that was Defensive Efficiency Rank. Evolutionary Analysis chose a lower limit of … well it set a lower limit, let’s just say that. This makes sense, if a lower seed has a defense that is ranked so far inferior to the higher seed, it is unlikely to prevail. A counter example is that the number of blocks per game was not a criteria that was chosen. In fact, most of the >200 criteria were not used, but that handful of around ten criteria set the filter that chooses a population of games that is more likely to contain a lower seed winning.
 
And that is one of the powerful aspects of this type of analysis, you don’t get the one key driver, or even two metrics that have a correlation. You get a whole set of filters that points to a collection of results that deviates from the “normal”.
 
Please join us as we test our result set this year. We’ll see if we get around 47%. Should be interesting!
 
If you have questions on this type of analysis or machine learning in general, please don’t hesitate to contact Gordon Summers of Cabri Group (Gordon.Summers@CabriGroup.com) or Nate Watson at CAN (nate@canworksmart.com).
**Disclaimer: Any handicapping sports odds information contained herein is for entertainment purposes only. Neither CAN nor Cabri Group condone using this information to contravene any law or statute; it’s up to you to determine whether gambling is legal in your jurisdiction. This information is not associated with nor is it endorsed by any professional or collegiate league, association or team. Machine Learning can be done by anyone, but is done best with professional guidance.
 
 
 

When should you Update Predictive Models?

New clients often have questions about why and how frequently CAN needs to update their predictive models.  Predictive models need to be updated because everyday new data is being created.  For example, your customers are buying more, subscribing or unsubscribing.  The environment is constantly changing.  While predictive models can handle a lot of new new data, overtime environmental changes build up causing predictive models to lose their effectiveness.  After a month, quarter, or a year it is necessary to update predictive models with new data.
As these new patterns emerge its important to periodically take time to investigate your data, update your models, and challenge your assumptions about your business. But how often should you do this?
(more…)

How Much Data Do I Need For Predictive Analytics?

Before beginning any predictive analytics project, its essential to investigate the breadth and depth of data available. However, at what point is it acceptable to say you have enough data to start?
The politically correct answer to this question is that it depends. Depends on what though?
Well for starters, certain types of data science and predictive analysis projects require more specific data requirements. In an extreme case, predicting survival rates of people or machines may require data spanning their entire lifespan. However, in most cases, data requirements are less stringent.
In most cases taking a snapshot of 3 to 5 years worth of data can yield a breadth of patterns surrounding consumer and business behavior. Why? (more…)

What Is Data?

We get asked all the time at CAN “what is data?”  “Data” is a term to describe facts, processes, or events that are able to be recorded and measured. Whether descriptive or quantitative, nearly anything can be converted into data. Facebook profiles, sales numbers, interest rates, zip codes, twitter tweets, emails, DNA sequences, and flight tracking information are all examples of data – and we have a lot of it. Data is collected from many different places, and while humans can collect data, machines and technology can collect far more and do it quicker. Computing systems are designed to collect massive amounts of data on the processes they observe or facilitate, yet most of this is never used. Data sits idle because no one has figured how to use it. Technology on the processing side and collecting side have nearly caught up and this is starting to make all the difference.
Thanks to these advances in computer processing power and storage capacity, 90% of the data available to humankind were nonexistent 2 years ago. Think about that for a minute. In other words, data are this age’s most abundant raw material. (more…)

Featured Posts – Click the Brain
Archives
CAN Jewels