Data analytics - what are they & why they matter for farmers

Updated: Jan 20

The number of data points farmers are capturing daily grows day-by-day. Yields, germination rates, land use, sales, planting & harvest events, and many more metrics make up the bulk of farm KPI’s (Key Performance Indicators). As the need for monitoring these metrics increases, farmers need tools that allow for easy, intuitive data analytics.

Data analytics are at the core of any growing farm in the digital age, and as we’re creating content around digital transformation for farms, it’s a topic that needs to be broken down and understood. Analytics have been the catalyst for monumental change for some of the world's largest brands, and those same effects are coming to farms all over the world as well. Let’s start with the basics, starting with...

Types of analytics

There are 4 primary types of data analytics (descriptive, diagnostic, predictive, prescriptive), broken up into two categories (backward & forward looking), and are the keys to unlocking the power to optimize your operations. We’ll start this conversation with the first category of data analytics...

1. Backward-looking analytics

No smoke-and-mirrors here: backward-looking analytics that look backwards. Data found here is historical, breaking down past events & their relevant data. There are two types of analytics considered backward-looking:


  • This data helps you answer questions about what happened, and provides essential insight into past performance. This data is mainly qualitative, using numbers & percentages to answer questions.

  • Examples of questions you’ll answer with descriptive analytics:

  • "What was my yield rate this harvest compared to last? Did I hit the sales projections I outlined pre-harvest? Did we operate at a profit this year?”


  • This data helps you answer questions about why things happened & is a direct confidant to descriptive. While descriptive is solely quantitative & and answers “what”, diagnostic is primarily qualitative & answers “why”; its purpose is to provide context to the numbers found using descriptive analytics.

  • Examples of questions you’ll answer with diagnostic analytics:

  • Why did my yield rate decline this year? Why did our sales increase by 20%? Why did operations operate at a larger loss despite increased sales?”

Backward-looking data is essential for any farm looking to paint a full-picture of what they’ve done in the past, particularly around sales and customer behavior. But we don’t live in the past, we live in the present, and the present is focused on making a better future. There are many tools that can help gather and analyze this data, though we encourage a system that integrates this information with other farm operation tools (which we outlined more in-depth in our conversation on Farm Management Software. Or feel free to reach out to me to save the read time & get directly relevant answers about what your farm wants to accomplish). This brings us to the second category of data analytics...

2. Forward-looking analytics

The flipside of backward-looking analytics, which focus on what's happened, forward-looking analytics focus on what will (or should) happen. Data found here is typically predictions of what will come based on historical data & analyzing trends in the industry as well as internal changes, and are key to understanding your farms trajectory moving forward. There are two types of analytics found here:


  • This data helps you answer questions about what could happen, and creates frameworks for potential future performance. This data can be both qualitative and quantitative, with a primary focus on predicting consumer behaviors (we wrote a bit about this already) & how they’ll affect your farm.

  • Examples of questions you’ll answer with predictive analytics:

  • “How will sourcing seeds from this supplier affect consumer sentiment for my products? Will COVID-19 help or hurt sales growth this harvest? What effect will changes in commodity produce have on our operating margins?”


  • This data helps you answer questions about what should be done, and are key to optimization of farm operations. This data can be both qualitative and qualitative, and is the “what-if” scenario machine that helps tackle multi-branching decision making (choosing between more than one course of action).

  • Examples of questions you’ll answer with prescriptive analytics:

  • “How will choosing sourcing from Johnny’s Seeds or Sarah’s Plantings affect my yield rates? Would cycling the grow zones each harvest lead to higher germination rates? How would operation margins be affected if you invested in D2C sales channels vs traditional middle-man supply chains?”

Forward-looking analytics leverage information gathered from backward-looking analytics with assumption of the future to give your farm insights into what will happen in the future, and how best to accomplish our goals within those market conditions. It should be noted forward-looking analytics are much harder to pinpoint given their uncertain nature and require powerful, technical tools to truly capture. Feel free to reach out to me and we can discuss what your farm is looking to forecast & how best to accomplish this!

Why analytics matter

Analytics matter because they work. We can talk about how millions of dollars are lost annually by businesses with poor data management, or how data analytics have optimized sales for businesses in nearly all industries & sizes, but we think the core reason to invest in analytics comes down to three activities. In business, activities must do one of three things:

  1. Increase revenue

  2. Decrease cost

  3. Decrease risk

Through analytics (and the proper tools to analyze data efficiently & effectively), you’ll have the ability to do all three. While this information only scratches the surface of what analytics are & what they can do for your farm, let’s keep the dialogue going! Leave a comment, share this on your socials, or let me know personally what ways you use your data or what ways you want to use them in the future.