By Matt Frizzo, operations analyst director with Carthage Veterinary Service
In addition to raising pigs, our industry is very diligent about collecting data from our operations and systems — in management software systems, feeding systems, animal movement planning systems and more. However, we have an opportunity as an industry with all this data to integrate it effectively for practical analysis.
Producers already have access to silos of data regarding sow performance, marketing, nutrition, grow-finish, weaning, and more, that they could start to put together to gain more insight into their finances and productivity. We have taken a Swiss Army knife approach to data collection, a little bit of everything. Now it is time for synthesizing and analyzing such data — and determining what you may still lack. It takes a little time, questioning, and strategy, but the rewards for doing so are measurable.
Decide on the data
To do an effective data analysis, it’s important to start with the right datasets. The quality of the data we have collected might not be as high as if we had been strategic earlier about defining and narrowing it down to “this is what we want to analyze, so these are the numbers we need to focus on collecting.” Beyond just collecting the right data, we need to think through how the data will be managed. Is it structured correctly in the right database so I can splice and dice it as needed? Who is going to have access to it? What kind of transformation of that data do we need? How is it going to be stored?
You can’t manage what you don’t measure, you will need multiple different data points to see the full picture and have an informed answer — but all of the pieces aren’t beneficial if they can’t be correlated or if they are only used in their silo. The data itself doesn’t tell us anything, we use that data to get information. Once we have the information, we can start to see what is going on in the business or system to either make adjustments or find questions that need further investigation. However, if we have the data but it isn’t structured the right way, then we don’t have the information to go on.
Doing the analysis
Next, decide how you will compare the data, or as I call it, “inspect what you expect” — determine what production baselines are for your purposes, and then compare the results with your expectations. Each operation or system is unique since you have a different marketing agreement, genetics program, feeding rations, and goals than other producers.
Future decisions
Embracing data analytics may not be easy at first. You may wonder if the ROI justifies the expense of collecting and storing data. If your initial response to using data analysis is, “I’m doing fine” — how do you know? Consider if you are certain there’s nothing new you could learn to make your operation more cost-efficient or to maximize your profit per animal.
Challenge yourself to be proven right. Or maybe even wrong. Consider that there are times when data analysis has helped a producer discover an issue they didn’t know they had, a problem they were able to solve while it was still relatively minor.
Once you do begin to see the value of using data analytics to spot what has been happening in your operation, you might even note trends from the past and present that you can extrapolate to future performance. This is the next step in data analytics: Predictive analysis. Simply put, this means looking ahead to what is likely to happen based on data — in addition to your own experience and judgment — and planning for what to do if particular situations arise as expected.
Read More:
A Good Start to 2024: Mortality Improves Across the Board in Latest MetaFarms Report
