Lesson 1 - Role of Data in Business Decisions

First Things First: Real-World Business Challenges

In this Module, you’ll apply your new skills to two real-world datasets from major retail companies: Rossmann and Walmart. These projects will help you understand how data analysts tackle real business problems using Excel and structured thinking.

Rossmann – Your Guided Project

Rossmann is one of Europe’s largest drugstore chains, operating over 3,000 stores across seven countries. One of their core challenges is accurately forecasting daily sales for each store. Reliable sales forecasts allow store managers to make better decisions around staffing, inventory, and promotions.

You’ll work with a curated version of Rossmann’s dataset throughout the guided lessons. This dataset is based on a public Kaggle competition, but we’ve prepared everything you need so you can focus on analysis without distractions.

Walmart – Your Practice and Independent Project

Walmart is the world’s largest retailer, operating thousands of stores globally. Like Rossmann, Walmart faces the challenge of understanding and predicting sales patterns — but with added complexity due to regional differences, holidays, and large-scale operations.

In the exercises and independent project, you’ll apply your skills to a curated Walmart dataset. You’ll explore how factors like holidays, promotions, and competition influence sales — and practice connecting data to real business decisions.

You don’t need to download anything from external websites. All datasets will be provided within the course materials in a clean, structured format, ready to use.

Key Considerations: These datasets will help you develop the mindset and technical skills needed to work as a professional analyst. As you work with these datasets, stay curious. Ask yourself not only how to answer questions, but also — how might the data mislead? Where are the gaps or assumptions? This is what distinguishes a technically capable analyst from a truly critical thinker.

What is Data?

For centuries, businesses relied on experience, instinct, and incomplete information to make decisions. Today, data has become the foundation for reducing uncertainty and improving strategic choices. But data is not truth on its own — it is a reflection of what we choose to measure, and how carefully we interpret it. As an analyst, your role is to navigate this complexity, transforming raw information into reliable knowledge that drives action.

At its core, data is simply recorded information — numbers, words, images, or observations captured from the world around us. In a business context, data might include sales transactions, customer feedback, inventory levels, or even weather reports.

But raw data is only part of the picture. Like ingredients in a kitchen, data alone doesn’t create value — it needs to be prepared, analyzed, and interpreted. That is the job of a data analyst: turning messy, scattered information into insights that help organizations make better decisions.

The Data Analytics Pipeline 

Turning raw data into actionable business decisions follows a systematic process known as the Data Analytics Pipeline. This process is used everywhere — from small businesses to global corporations — to make better, evidence-based decisions.

Here’s how top-performing companies approach data analysis:

1. Define the Business Problem

Before opening a spreadsheet or querying a database, analysts must first understand:

• What decision are we trying to support?
• What problem needs solving?

Examples:

• At Netflix, the business problem might be: “How can we recommend content that keeps viewers engaged?”
• At Walmart, it could be: “How do holidays impact sales patterns across regions?”

Without a clearly defined question, even perfect data won’t lead to useful insights.

2. Collect Relevant Data

With the question in mind, the next step is gathering data that might help answer it. This could include:

• Internal data (sales, customer behavior, operations)
• External data (market trends, competitor information, public data)

Example:

• Amazon collects customer purchase histories, product reviews, and browsing patterns to inform recommendations and inventory decisions.

3. Clean and Prepare the Data

Raw data is often messy — with missing values, duplicates, or inconsistent formats. Analysts spend significant time preparing clean, structured datasets.

Example:

• Airbnb ensures listing details, prices, and availability data are standardized globally before analysis can happen.

4. Exploratory Data Analysis (EDA)

EDA helps analysts get familiar with the data, spotting patterns, anomalies, or relationships.

Example:

• At Spotify, EDA might reveal that certain songs are consistently skipped after 30 seconds, prompting further investigation into user behavior.

5. Apply Analytical Techniques or Build Models

Once familiar with the data, analysts use techniques like:

• Descriptive statistics
• Forecasting
• Hypothesis testing
• Predictive models

Example:

• Zara uses forecasting models to predict fashion trends and optimize inventory, reducing waste and staying ahead of customer demand.

6. Communicate Insights

The most brilliant analysis is wasted if it cannot be understood. Clear visualizations, concise reports, and business-focused language ensure insights reach decision-makers effectively.

Example:

• Microsoft analysts present executive dashboards tracking cloud service performance — enabling leaders to act quickly when metrics deviate from targets.

7. Drive Actionable Recommendations

The final — and most important — step is translating insights into concrete business actions. Data is valuable when it leads to improved decisions and business outcomes.

Example:

At Starbucks, data on customer preferences informs decisions about new product launches, store locations, and marketing campaigns.

This structured process applies universally — whether you’re an analyst at a global tech giant or working on a project for a retail company. In this module, you’ll follow the same process as you work with real-world data to solve practical business problems.

Consider Rossmann, the retail company we introduced earlier. Their store managers rely on accurate daily sales forecasts to schedule staff effectively and manage promotions. Behind the scenes, that process follows a classic analytics pipeline: raw sales, customer, and store data is collected, cleaned, analyzed, and translated into actionable forecasts that directly impact business operations.

Throughout this module, you will apply this pipeline practically using MS Excel — still one of the most widely used tools for business data analysis.

Key Consideration: As you work through this process, consider: Where in this pipeline could AI tools assist you? And where is human understanding — of context, nuance, and judgment — still irreplaceable?

The Day-to-Day Work of a Data Analyst

Data analysts are often described as part detective, part translator, and part problem-solver. On a typical day, you might find yourself working through several key tasks:

• Data Preparation: Cleaning and organizing datasets using tools like Excel to ensure accuracy and consistency.

• Exploratory Analysis: Using formulas, PivotTables, and visualizations to uncover patterns and trends hidden in the data.

• Identifying Business Insights: Connecting patterns in the data to real-world business challenges and opportunities.

• Communicating Results: Creating clear charts, dashboards, or reports that help stakeholders understand the story behind the numbers.

• Collaborating with Teams: Engaging with business units — such as marketing, operations, or finance — to ensure you’re addressing relevant problems and providing actionable recommendations.

While mastering technical skills is important, what truly distinguishes successful data analysts is a blend of curiosity, structured thinking, and a strong understanding of the business context. These qualities enable analysts to not only find patterns in the data but also interpret what those patterns mean for the company’s strategy and operations.

For example, at Rossmann, an analyst might start the day by preparing historical sales data in Excel, investigating patterns related to promotions or holidays, and building reports that help store managers plan staffing or stock levels. While the technical work happens in spreadsheets or tools, the business impact is felt on the shop floor.

Let’s not forget: It’s not only your technical skills or business knowledge that define your impact — but how you communicate your work and present yourself as a credible professional. Your reputation as a thoughtful, reliable analyst begins to form long before your first job interview.

Data Roles and Responsibilities

Framing Business Questions

At the heart of every data project lies a deceptively simple question: What problem are we trying to solve?

Too often, analysts – especially early in their careers – jump straight into datasets or tools without pausing to clarify the business problem. The result? Impressive charts, but irrelevant insights, and no real business impact.

Your ability to frame clear, relevant business questions is one of the most valuable – and underestimated – skills you will develop as a data analyst. This skill separates those who simply work with data from those who help drive real decisions.

Turning Data into Decisions

Raw data, on its own, rarely provides answers. It is only through asking the right questions that data becomes meaningful.

Consider Rossmann, the European retailer we introduced earlier. Their store managers need to make daily operational decisions — from staffing levels to promotional strategies — based on data. But no one hands them neatly packaged insights. The analyst’s job is to start by asking the right business questions, such as:

• How do state holidays affect daily sales at different store locations?
• Does proximity to a competitor influence sales trends?
• Are certain promotions more effective for stores with extended assortments?

These questions are not technical in nature – yet they shape every step of the analysis that follows. Poorly framed questions lead to wasted time, irrelevant findings, and lost trust. Good questions lay the foundation for meaningful, actionable insights.

What makes a Good Business Question

A well-framed business question typically:

• Focuses on a real problem or opportunity faced by the organization.
• Is specific enough to guide analysis, but broad enough to allow exploration.
• Connects clearly to decisions, actions, or business outcomes.
• Respects the context — the business environment, goals, and constraints.