Technical Report on Sales Data
Introduction
This report uses a sales dataset for a company's products, aiming to familiarize ourselves with the data, identify key patterns, anomalies, and gain initial insights.
Project Background: The objective of analyzing this sales dataset is to uncover insights that can inform business strategies, improve sales performance, and enhance customer satisfaction. Understanding sales patterns and identifying key drivers of revenue can help in optimizing marketing efforts and inventory management. This project was done as a task for HNG11 internship (https://hng.tech/internship)
Data Cleaning: Data cleaning involves handling missing values, correcting inconsistencies, and ensuring the data is in a suitable format for analysis. The tool used for this process is Microsoft excel. The process of cleaning the dataset involved removing duplicates, blank cells and ensuring that the headers have clear and concise header names and using underscores between words to make it easier to analyse. The data was sorted by order_date column.Order_date column was changed to short date format, that included removing the time stamps. Observations The dataset contains 2,821 rows and 25 columns.
Obvious Patterns: Sales are recorded for a variety of products under different product lines. There is a notable variation in the quantity ordered and the price per item across different transactions.
Trends: Some countries appear to have higher sales volumes, suggesting a potential geographical pattern in sales distribution.
Anomalies: There are a few records with extremely high or low sales values, which may require further investigation to determine if they are outliers or data entry errors. Basic Visualizations: Sales by Country: A bar chart displaying total sales by country highlights which regions contribute the most to overall revenue. From the chart, USA recorded the highest total sales.
Product Line Performance: A bar chart comparing total sales across different product lines reveals which product categories are the most and least successful. Base on the chart, Classic cars are the most successful product while Trains are the least successful products
Conclusion
The initial exploration of the sales data has provided several valuable insights:
USA, Spain and France significantly outperform others in terms of total sales, indicating potential key markets.
Classic cars, vintage cars and motorcycles generate higher sales, suggesting these categories are more popular or profitable. By continuing to analyze this dataset, we can uncover deeper insights that can drive strategic business decisions and improve overall sales performance.
If your interested in harnessing your data analysis skills be sure to visit this website https://hng.tech/internship