From Describing to Prescribing: How Understanding Four Types of Analysis Will Transform Your Business

You're staring at your monthly Shopify sales report.

The numbers are there – up 3% from last month. Great news - right?!

But does this really tell you...

• Why did sales increase?

• Which products drove that growth?

• Will this trend continue?

• What should you do differently next month?

If you're asking these kinds of questions on a regular basis, you're not alone.

Most business owners know there's more to their data than what standard reports show, but figuring out how to get those deeper insights can be pretty overwhelming.

Moving beyond basic reporting to create ways to answer these more impactful questions isn't easy, especially when you're already juggling everything else required to run your business.

And let's be honest – platforms like Shopify don't make it easy to break down your data in these ways.

There are commercial reasons for this – they want you to pay for reporting upgrades and premium analytics! The basic reporting they provide keeps you in the realm of descriptive analytics, the most elementary form of data analysis.

So what can be done to change this?

This challenge is exactly what motivated me to start Square Goose.

Throughout my career working with retailers of all sizes, I've seen how transformative it can be when businesses move beyond descriptive analysis toward more sophisticated approaches.

I wanted to help brands make this transition without requiring the resources of a major corporation.

There's nothing more satisfying than watching a small business owner's decision-making power multiply when they gain access to insights previously reserved for big players with dedicated analytics teams.

Let me share how I've seen this evolution unfold, and how you can advance your own analytics journey.

The Analytics Evolution: Four Stages of Business Intelligence

1. Descriptive Analytics: What Happened?

Descriptive analytics is exactly what it sounds like – it describes what happened in your business. This is your standard Shopify dashboard showing:

• Total sales for the month

• Number of transactions

• Average order value

• Top-selling products

  
  

While valuable as a starting point, descriptive analytics only tells part of the story.

It's like looking at the scoreboard after a football match – you know the result, but not how the game was played.

(For any fellow Man Utd fans, this isn't necessarily a bad thing at the moment!)

I remember working with a clothing retailer who relied solely on their e-commerce platform's standard reports.

They could see their sales were declining but had no insight into why.

They were making decisions based on incomplete information, essentially driving while only looking in the rearview mirror.

The limitation is clear – when you only know what happened, your decision-making is reactive rather than proactive.

You might cut prices when sales drop or increase inventory of top sellers, but these knee-jerk reactions often fail to address underlying issues or capitalize on hidden opportunities.

We should all be looking to dig deeper into data, which is where Diagnostic analysis comes into play...

2. Diagnostic Analytics: Why Did It Happen?

This is where the real insight begins. Diagnostic analytics digs into your data to understand the "why" behind the numbers.

I experienced this transformation firsthand while working with a large international manufacturer who was concerned about losing key B2B customers to competitors.

Their initial data showed declining sales across several major accounts – a concerning trend that, on the surface, suggested customer dissatisfaction.

But when we implemented diagnostic analytics, a completely different story emerged:

• While overall sales to these accounts had decreased, certain product lines were actually showing growth

• Inventory availability issues were the primary driver behind lower customer satisfaction scores

• Customers who received proactive communication about low inventory levels (before placing regular, timed orders) reported significantly higher satisfaction

  
  

This deeper understanding completely shifted their approach to customer relations.

Instead of launching an expensive customer retention campaign or slashing prices, they improved their inventory forecasting and implemented an automated communication system to alert customers about potential availability issues.

The result?

Customer churn reduced drastically, leading to savings of over $11m in the first quarter!

Without diagnostic analytics, they would have been treating symptoms rather than the actual disease.

That's the transformative power of asking "why?".

With diagnostic analytics, your decisions shift from reactive to responsive.

You're no longer guessing at solutions but targeting specific, identified issues.

This brings a level of precision to your decision-making that can dramatically improve outcomes while often reducing costs.

For business leaders, this means moving from "something's wrong, we need to do something" to "here's exactly what's happening, and here's the targeted solution."

The confidence this brings to your organization is immeasurable – teams align more quickly around solutions when they understand the true nature of the problem.

3. Predictive Analytics: What Will Happen?

Once you understand what happened and why, you can begin looking forward.

Predictive analytics uses historical data patterns to forecast future outcomes.

One of my most fun projects involved creating a sales forecasting tool for a major grocery retailer who needed to predict sales volumes for new products – a notoriously difficult challenge since there's no sales history to base forecasts on.

Traditional approaches would have relied on category-level forecasts or basic comparisons to "similar" products.

But we developed a more sophisticated approach:

• We analyzed sales histories of products in the same categories

• We broke down product names and descriptions into detailed components (for meat products: cuts, cooking methods, flavors, spices)

• We cross-referenced those keywords against similar products with established sales histories

• We combined these insights with variables like store location, seasonality, and even weather forecasts

  
  

The results were transformative.

The retailer saw an 18% increase in sales while simultaneously reducing waste from overordering by 25% – contributing millions of pounds to their bottom line in the first year alone.

But beyond the immediate financial impact, predictive analytics fundamentally changed how the business operated.

Product launches, previously viewed as high-risk gambles, became data-driven strategic moves.

Buyers negotiated with suppliers with greater confidence, knowing they could accurately predict demand. Store managers trusted their inventory allocations rather than hoarding stock "just in case."

This is what predictive analytics does for your business – it transforms uncertainty into calculated risk.

Instead of hoping your decisions will work out, you're making moves based on probable outcomes.

The entire emotional landscape of decision-making shifts from anxiety to confidence.

Imagine starting your day with clear visibility not just into what happened yesterday, but what's likely to happen tomorrow.

How would that change your approach to challenges?

How much more boldly might you pursue opportunities?

This forward-looking perspective is what separates businesses that merely survive from those that strategically thrive.

4. Prescriptive Analytics: What Should We Do?

This is the pinnacle of analytics maturity.

Prescriptive analytics not only predicts what will happen but recommends specific actions to optimize outcomes.

I recently led a project for a specialty retailer struggling with their product assortment decisions.

They needed to understand the complex impact of adding or removing products within certain categories.

We developed a prescriptive analytics system that:

• Identified which products could be safely eliminated with minimal sales impact

• Predicted which new products would drive the highest incremental revenue (not just cannibalizing existing sales)

• Factored in availability constraints to prioritize reliable, high-margin products

• Created store-specific recommendations based on local customer preferences

  
  

The system didn't just provide data – it delivered specific, actionable recommendations: "Replace these 27 products with these 14 new ones in these specific stores."

But the true power of prescriptive analytics lies in how it transforms organizational decision-making.

Category managers, once bogged down in spreadsheet analysis and second-guessing, could now focus on supplier negotiations and strategic planning.

Store managers spent less time managing inventory issues and more time developing their teams and serving customers.

Prescriptive analytics doesn't just tell you what will likely happen – it guides you toward the best possible future.

It's like having a business GPS that not only shows your destination but identifies the fastest route, warns of traffic ahead, and suggests alternatives when conditions change.

For business leaders, this means replacing the burden of endless decision trees with clear, data-backed pathways forward.

The mental energy formerly spent on "what if" scenarios can now be directed toward innovation and growth.

You're no longer just reacting to your business environment – you're actively shaping it.

Breaking Free from Descriptive-Only Analysis

One of the things I'm most passionate about at Square Goose is helping clients move beyond basic reporting to unlock the full value of their data.

Here's how you can begin that journey:

Start Asking Better Questions

The shift from descriptive to diagnostic begins with curiosity.

Instead of accepting that sales are up 3%, ask:

• Which product categories drove that increase?

• Did the increase come from new customers or existing ones?

• Was the growth consistent across all regions or concentrated?

• Did marketing activities influence the uptick?

  
  

I've found that simply teaching teams to ask these "why" questions transforms how they approach data analysis.

Break Down Your Data into Dimensions

To diagnose effectively, you need to examine your data from multiple angles:

• Time dimensions: Daily, weekly, monthly trends

• Product dimensions: Categories, price points, features

• Customer dimensions: New vs. returning, demographics

• Geographic dimensions: Regions, urban vs. rural, proximity to competitors

• Marketing dimensions: Channel, campaign type

  
  

Visualize Your Data Effectively

Visualization is crucial for diagnostic analysis.

The right chart can instantly reveal patterns that would be invisible in a spreadsheet.

Some effective visualizations for diagnostic analysis include:

• Heat maps: Showing performance across multiple dimensions simultaneously

• Scatter plots: Revealing relationships between variables

• Trend lines with annotations: Highlighting the impact of specific events

• Comparison charts: Contrasting performance across segments

  
  

I love the moment when a client sees their data visualized properly for the first time. There's often an "aha!" moment when patterns suddenly become clear.

Structure Your Data for Interrogation

To move beyond basic reporting, your data needs to be structured in a way that supports deeper analysis.

This means:

• Organizing data into fact tables (sales, inventory) and dimension tables (products, customers, time)

• Ensuring consistent definitions across your business

• Creating a single source of truth for key metrics

• Implementing systems that make it easy to drill down into details

  
  

This might sound technical, but it doesn't have to be complicated.

Even organizing your spreadsheets consistently can make a huge difference in your ability to diagnose issues.

Build Simple Predictive Models

Once you're comfortable with diagnostic analysis, you can begin incorporating predictive elements:

• Use trend lines to project future performance

• Incorporate seasonality factors to adjust forecasts

• Build simple "if-then" scenarios to test different assumptions

• Compare forecasts to actuals and refine your approach

  
  

The Personal Impact of Better Analytics

What I love most about my work at Square Goose isn't the technical aspects – it's seeing how better analytics changes how business owners think and operate.

I founded Square Goose because I wanted to bring the sophisticated analytics capabilities of large retailers to smaller brands that have just as much potential but lack the resources for a full BI team.

Your Next Steps

No matter where you are in your analytics journey, you can take these steps to advance to the next level:

1. Audit your current reporting: What questions are you answering? What questions remain unanswered?

2. Pick one business challenge: Choose a specific issue and explore it from multiple dimensions

3. Experiment with visualization: Try representing your data in different formats to see what insights emerge

4. Invest in data structure: Organize your data in a way that supports deeper analysis

5. Start simple with predictions: Begin incorporating trend lines and basic forecasts

   
   

Remember, this isn't about having the most sophisticated tools or hiring a team of data scientists.

It's about adopting an analytical mindset that constantly asks "why?" and "what's next?"

Whether you're just starting out or looking to take your analytics to the next level, the journey from descriptive to prescriptive analytics can transform how you understand and grow your business.

Ready to elevate your data analysis and decision-making?

Let's explore how Square Goose can help you unlock the full potential of your business data.