Video Games Sales

DATA VISUALISATION

HIMANK BHATEJA-8A
EKANSH GOYAL-6A
SAMPADA YADAV-22A
MILAN ADLAKHA-16A
TUSHAR KAUL-27A
01 - Introduction
02 - Steps of cleaning
03 - Data Visualization
04 - Conclusions

Data Visualization
 Analyzing data
01 - Introduction enables informed
decision-making
It analyzes video game sales data from multiple dimensions. Our primary
goal is to extract actionable business insights that inform product strategy,
marketing decisions, and regional focus. We’ve developed a suite of
visualizations—including bar charts, line charts, scatter plots, and an
interactive regional sales map—to answer key questions about sales
performance and market trends. In particular, the interactive regional sales
map helps us understand which publishers excel in specific regions, allowing
decision-makers to tailor their strategies accordingly.
Data

Visualization
PROBLEM STATEMENT
The raw data collected from various sources contains inconsistencies, redundant
information, and a high volume of missing or null values that compromise the
reliability of subsequent analyses. The objective is to transform this raw data into
a clean, consolidated master dataset ready for effective data visualization. This
involves merging multiple data sources, removing unnecessary fields, automating
repetitive cleaning tasks, handling missing values, eliminating columns with
excessive nulls, and identifying and rectifying outliers and inconsistencies. The
final outcome is an Excel file containing a refined dataset that supports accurate
and insightful data visualizations.

Data

Visualization
 02 - Steps of cleaning raw
data into usable format
Step 1- DATA CONSOLIDATION
AND PREPARTION

a. Gather and Merge Data:

Import raw data files from various sources into one master dataset.
Merge datasets using unique identifiers (e.g., game ID) to create a unified data table.
b. Remove Unnecessary Columns and Fields:
Identify and delete columns that are not needed for analysis.
Retain only the essential fields (e.g., sales figures, ratings, genres, publishers).

Step 2- DATA CLEANING AND

AUTOMATION

a. Eliminate Columns with Excessive Null Values:

Identify columns with a high percentage of null or missing values.
Remove those columns if they do not contribute to your analysis.
b. Handle Missing Values:
Use techniques such as imputation or deletion based on the importance of missing fields.
Ensure that missing values are consistently handled across the dataset.
c. Automate Repetitive Cleaning Tasks with Macros:
Write and run macros to standardize data formats, remove duplicates, and perform bulk cleaning operations.
Automate recurring tasks like trimming spaces, correcting data types, and renaming columns.
STEP 3- DATA FINALIZATION
AND VALIDATION
a. Check for Outliers and Inconsistencies:
Identify outliers using statistical techniques or visual inspection.
Correct or remove inconsistent entries that could skew the analysis.
b. Validate Data Integrity:
Cross-check key metrics (e.g., sales totals, rating distributions) against known benchmarks.
Ensure that all fields adhere to expected data types and formats.
c. Generate Final Dataset:
Save the cleaned and validated master dataset as an Excel file.
 Drag Fields:
Genre to Rows, Global_Sales (SUM) to
Columns.
Enhance:
Sort bars in descending order and add mark
labels.
Use color to differentiate genres

Bar Chart: Genre vs. Global Sales

Set Up:
Drag Year_of_Release (as continuous) to Columns and
Global_Sales (SUM) to Rows.
Enhance:
Use the Pages shelf for optional animation.
Customize tooltips for added context.
Data

Line Chart: Global Sales Over Time Visualization

Parameter-Driven Bar Chart: Regional Publisher Sales

Create Parameter:
Build a “Select Region” parameter with values “Global”, “NA”, “EU”, “JP”.
Calculated Field:
Create “Region Sales” using a CASE statement to choose the proper sales
field.
Build Chart:
Drag Publisher to Rows and Region Sales to Columns.
Data
Show parameter control for dynamic region selection
Visualization
Heat Map:
Drag Genre to Columns, Platform to Rows, and Global_Sales to Color.
Tree Map:
Drag Publisher to Detail and Global_Sales to Size, then switch to Tree Map view.
Box Plot:
Drag Genre to Columns, Critic_Score (or User_Score) to Rows, and add a Box Plot overlay.
Stacked Bar Chart:
Drag Genre to Rows, Meas
 Drag Fields:
Critic_Score to Columns and User_Score to Rows.
Enhance:
Set mark type to Circle.
Drag Global_Sales to Size and add trend lines.
Edit tooltips to include game details.

Data
Scatter Plot: Critic
vs. User Scores Visualization
03 - DASHBOARD
 Data Visualization and their
business insights
BAR CHART: GENRE VS. GLOBAL SALES
Purpose: This chart shows which video game genres drive the highest global sales.
Business Insight: Identifying high-performing genres helps in prioritizing investments in game development and targeted marketing campaigns.

LINE CHART: GLOBAL SALES OVER TIME

Purpose: The line chart visualizes global sales trends across years.
Business Insight: By examining sales fluctuations over time, we can uncover seasonal patterns, the impact of major industry events, or shifts in consumer demand.

SCATTER PLOT: CRITIC SCORE VS. USER SCORE

Purpose: This scatter plot explores the relationship between critic scores and user ratings, with bubble sizes reflecting sales volumes.
Business Insight: Understanding the correlation between critic and user scores enables companies to assess product quality, align their marketing narratives, and
identify outlier games that perform unexpectedly.

PARAMETER-DRIVEN BAR CHART: REGIONAL PUBLISHER SALES

Purpose: Through a dynamic parameter control, this chart compares publisher performance across different regions (Global, NA, EU, JP).
Business Insight: It reveals regional strengths and weaknesses among publishers. For instance, a publisher might perform exceptionally in North America but not in
Europe, which could indicate the need for localized marketing strategies or product adaptations.

INTERACTIVE REGIONAL SALES MAP

PURPOSE: THIS MAP USES GEOGRAPHIC DETAILS AND DYNAMIC COLOR CODING TO VISUALLY REPRESENT PUBLISHER SALES INTENSITY BY REGION.
Business Insight: By switching between regions using the parameter control, stakeholders can quickly identify which publishers excel regionally. This spatial analysis
is crucial for optimizing distribution channels, targeting advertising, and expanding into underperforming markets.

ADDITIONAL VISUALS (HEAT MAP, TREE MAP, BOX PLOT, STACKED BAR CHART):
Heat Map (Genre vs. Platform Sales): Highlights which combinations of genres and platforms drive high sales, uncovering niche opportunities.
Tree Map (Publisher Market Share): Illustrates the relative market share of publishers, facilitating competitive analysis.
Box Plot (Score Distribution by Genre): Displays the spread and consistency of critic and user scores, flagging genres with high variability or quality concerns.
Stacked Bar Chart (Regional Sales Breakdown by Genre): Breaks down genre performance across regions, guiding decisions on regional product launches or
promotions.
04 - Conclusions Data analysis helps in
identifying outliers or
anomalies in the data
Transformed fragmented, messy raw data into a unified master
dataset.
Merged multiple data sources using unique identifiers.
Removed unnecessary columns and fields to streamline analysis.
Eliminated columns with excessive null values. Data
Handled missing values using appropriate imputation or deletion
strategies.
Visualization
Automated repetitive cleaning tasks with macros for efficiency.
Checked for outliers and inconsistencies to ensure data integrity.
Generated a clean, final Excel dataset ready for accurate data
visualization and business analysis. Data analysis facilitates
predictive modeling and
forecasting
Thanks