E Commerce Sales Data Analysis Using Excel Kaggle

Contributions to enhance the analysis or address any insights are welcome! Please feel free to submit a pull request or open an issue. Excel Tutorial on Sales Data (Using Kaggle Dataset) Today we take raw sales data and turn it into actionable business insights using Excel’s built-in tools no code needed. The dataset includes these key columns like Sales, Quantity, Shipping Cost OfficeRegion, USCA, LATAM, Tech (product indicator) What do we do? 1. Data Cleaning Formatted Sales and Shipping Cost as Currency Ensured Quantity is a whole number Replaced 0/1 flags in Office and Tech with labels like Main Office / Branch, Tech / Non-Tech Checked for...

Checked for Missing Values & Removed Duplicates → Applied filters and used COUNTBLANK() to spot blanks → Used Data → Remove Duplicates to clean repeated rows After cleaning the data, I jumped into core... I built a Pivot Table to break down total sales by office region : a quick way to spot which branches are performing best. Then, I compared quantity sold across Tech vs Non-Tech products using labeled columns and a simple category-based pivot. Finally, I calculated the average shipping cost per office and region, helping identify areas where logistics might be optimized. All done with Excel’s drag-and-drop PivotTable tool : no formulas needed, just clean structure and clear insights. Insights from the Sales Dataset Analysis Top-Performing Offices: The Pivot Table showed that the Main Office (or a specific office name, if available) generated the highest total sales — a clear regional leader in...

This helps the business identify strong markets or teams. Tech vs Non-Tech Sales: Tech products accounted for a higher share of quantity sold, but not necessarily the highest revenue. This could suggest tech sells in volume but may have lower unit prices — useful for pricing or marketing strategy. Shipping Cost Variability: Average shipping costs were significantly higher in certain offices or regions (e.g., LATAM vs USCA), which may indicate logistical inefficiencies or areas where cost-saving strategies could be introduced. Low-Performing Regions or Categories: Some offices had strong quantity numbers but lower sales, signaling either high-volume, low-value orders or discounted pricing — a flag for deeper investigation. Data Analyst | Finance Analyst| Project Manager | Business Intelligence | Turning Data into Insights | SQL| Power Bi| Python | Excel| Tableau

Sales & Revenue Analysis Project Turning Data into Decisions: Sales & Revenue Analysis Dashboard As part of my ongoing project to strengthen my expertise, I recently built a Sales & Revenue Analysis dashboard designed... Here’s a quick walkthrough of my process: Problem Statement The goal was to understand sales performance across product categories, regions, and customer segments, helping identify high-performing areas and uncover growth opportunities. Process 1. Data Extraction: Pulled raw data from the company SQL database. 2. Data Preparation: Cleaned and standardized the dataset in Excel.

3. Data Modeling: Created relationships and calculated KPIs such as total revenue and average sales per transaction. Visualization: Built an interactive Power BI dashboard using slicers for Region, Customer Segment, and Product Category, allowing dynamic exploration of trends. Tools Used 1. SQL: Data extraction and transformation 2. Excel: Data cleaning and aggregation 3.

Power BI: Dashboard design and visualization Insights 1. Total sales for 2023/2024 were $14.92M, with an average transaction of $1.78K. 2. Technology products were the top-selling category at $6M, followed by furniture and office supplies. 3. Region-wise, the West led at $3.6M, while Quebec had the lowest sales ($1.5M).

4. Segment-wise, the analysis showed corporate customers contributed the highest sales ($5.5M). 5. Cross-analysis indicated that corporate segments prefer technology products, while home office and consumer segments and small businesses purchase a mix of the product categories. By consolidating multiple data and visualizing the results, the dashboard provided clear visibility into performance drivers and supported data-informed decisions for pricing, marketing, and resource planning. This project demonstrates my ability to blend financial analysis, data modeling, and visualization to deliver insights that drive operational and strategic decisions.

The Sales Team Dashboard in Power BI tracks individual and team performance metrics, including targets achieved, deals closed, and pipeline status. It helps managers monitor productivity, recognize top performers, and optimize team strategies to drive overall sales success. Read More : https://lnkd.in/g-KK6vUC #Single_vs_Bidirectional_Relationship (#Cross_Filter_Direction) Last week, while building a Power BI report, my sales numbers looked off After checking the model — the issue was the relationship direction! Let’s see what that means 👇 🔁 Scenario 1: Single Direction Relationship You have two tables: * Customers → CustomerID, City * Sales → CustomerID, SalesAmount If the relationship is Single Direction (Customers →... > When you select City = Delhi, only related sales appear.

> But filtering “Sales > ₹5000” won’t affect the Customers table. > Use Case: Perfect for simple one-to-many relationships like Customer → Sales or Product → Sales. It keeps the model clean and fast. #Scenario 2: Bidirectional Relationship Now imagine you also have a Support Tickets table with CustomerID. You want to see: “How many customers who made purchases also raised support tickets?” Here both Sales and Support Tickets rely on Customers. To make filters flow between them (e.g., filter on Sales also affects Tickets), you use a Bidirectional Relationship on the CustomerID link.

>Now filters move both ways — so selecting customers with sales also filters support tickets for those same customers. > Use Case: Needed when two tables must filter each other through a common field. DAX #CROSSFILTER — Think of CROSSFILTER as a way to temporarily switch between Single and Bidirectional inside a DAX formula. If your model has a Single Direction relationship (Customers → Sales), but you need it to behave Bidirectional only for one calculation — use: CALCULATE( [Total Sales], CROSSFILTER(Customers[CustomerID], Sales[CustomerID], BOTH) ) > BOTH makes... No need to change the actual model! You can also switch it back using CROSSFILTER(..., NONE) or ONEWAY as needed.

Summary 1️⃣ Use Single Direction for most relationships (faster & simpler) 2️⃣ Use Bidirectional only when both tables must filter each other 3️⃣ Use CROSSFILTER in DAX to temporarily apply bidirectional logic Looking for... I offer practical training that goes beyond theory — happy to share details, just drop me a message. 📞 +91-9599856867 | 📧 Datavizz985@gmail.com Shajan Reynold Anushka Tripathi Afroz Ibrahimi Sanjay Verma Rahmani Hasan Dr. Jiyaul Mustafa, FIE Chandan Kushwaha #PowerBI #DataModeling #DAX #PowerBILearning #DataAnalytics #MicrosoftPowerBI #Trainer #Mentor This project involves a detailed analysis of one week of Shopify e-commerce sales data sourced from Kaggle. The analysis was conducted using Microsoft Excel and Power BI.

To identify top-performing products, sales patterns, customer trends, and areas for improvement in inventory and order management. Kaggle – Shopify E-commerce Dataset (add exact link if available) Power BI Dashboard Snapshot (or wherever you've hosted it) The primary objective of this analysis is to derive insights from the Superstore’s sales data to answer the following key questions: As the General Manager, I want to identify the bestselling products and the recent trends, so that I can decide on which products would be best to run marketing campaigns on to generate a... The data for this analysis is sourced from the Superstore Sales dataset, which includes detailed information on orders, returns, users, and various dashboards and pivot tables.

The dataset comprises multiple sheets: The data is sourced from Kaggle (an Excel extract), see here to find it The project is divided into several stages: Kaggle, a trusted platform for data science competitions and datasets, currently hosts several ecommerce datasets that are essential for research and business analytics in 2025. These datasets cover diverse aspects of ecommerce transactions, ranging from sales prediction to payment analysis and discount optimization. For example, one of the most up-to-date datasets details transactions from January 2025 to June 2025 for a registered online ecommerce store based in Pakistan.

Others include synthetic online retail sales data that mimic real-world transaction patterns, plus collections designed explicitly for sales forecasting. Explore these datasets directly on Kaggle: Data is at the core of strategic decision-making in ecommerce. With competition fierce and customer expectations high, businesses that harness ecommerce data tend to outperform those relying on intuition alone. How does the Kaggle ecommerce dataset enhance your ecommerce strategy? By applying machine learning models to Kaggle datasets, businesses can forecast product demand more accurately, preventing overstock or stockouts.

This optimization not only reduces holding costs but ensures customers find what they want when they visit your online store.

People Also Search

• E-Commerce Sales Data Analysis Using Excel | Kaggle
• Kai-Zhang-DA/E-Commerce-Data-Analysis-in-Excel - GitHub
• Turning Sales Data into Strategy: How I Uncovered Insights Using Excel ...
• Ecommers Sales Analysis | Kaggle
• Excel Tutorial on Sales Data (Using Kaggle Dataset) - LinkedIn
• GitHub - prakashjaypandey/Shopify_data_Analysis: # Shopify Sales Data ...
• SuperStore Sales Analysis | Akash Bhargav
• E-commerce Sales Data Analysis and forecasting future sales using Excel ...
• Harnessing Kaggle Data for Ecommerce Growth
• ECOMMERCE- ANALYSIS | Kaggle