COMPARATIVE ANALYSIS

ON POPULAR GAMES
BETWEEN 1980-2023

Submitted by:
Tushar Kapoor,
Sumit Dabas
 Introduction
The gaming industry is a dynamic and
rapidly evolving entertainment sector
Gaming
that combines technology, creativity, Industry

and community to provide immersive

interactive experiences.

Bussiness problems: Objective 01

Finding insights into future trends,
Predictive Game Development aiding in the planning and
01
development of games

Objective 02
Player Engagement Optimization Identify patterns that
02 enhance engagement

Objective 03
03 Resource Allocation Optimizing development
budgets, manpower, and time.
 Some Important
Concepts
Python Machine Learning Algorithms

Machine Learning is the field of

Python is a high-level, versatile
study where computers learn An algorithm is a set of instructions
programming language
from data and improve their for solving a specific problem or
emphasizing readability and
performance on a task without accomplishing a task.
simplicity.
being explicitly programmed..
 Data Description
This dataset contains a list of video games dating from 1980 to 2023, it also
provides things such as release dates, user review rating, and critic review rating.

Plays: Number of users that

01 Title: Title of the game 06 have played the game before
Release Date: Date of release
02 of the game's first version 07 Wishlist: Number of users who
wish to play the game
03 Rating: Average rating 08 Reviews: User reviews
Genres: All genres pertaining to
04 a specified game 09 Backlogs: Number of users who
have access but haven't started
05 Lists: Number of users who 10 Playing: Number of current
listed this game users who are playing the game.
Highest Rated Games
Top Trending Categories
Process
 Basic Exploration

Reading the data

Some Information
Cleaning
the Data
Dropping unwanted columns

Finding and Dropping Null values

 Changing the Data Type

Changing column names to lower case

 Number of players for each category

Histogram for rating

Distribution of Ratings
Relationship between Rating and
Number of Reviews

Top Rated games in 2021

 Random Forest Regression
Random Forest is an ensemble learning method that combines multiple decision trees to
improve predictive accuracy and control overfitting.

Since the random forest combines

multiple trees to predict the class of the
dataset, it is possible that some
decision trees may predict the correct
output, while others may not. But
together, all the trees predict the
correct output. Therefore, below are
two assumptions for a better Random
forest classifier:
There should be some actual values
in the feature variable of the dataset
so that the classifier can predict
accurate results rather than a
guessed result.
The predictions from each tree must
have very low correlations.
 Implementing
Random Forest Regressor
Step 1: To find the outliers from our dataset and removing them
Step 2: To seprate our data into features and target

Step 3: Splitting data into train and test.

Defining, fitting the model and making predictions
Step 4: Finding the R2 Score for our model

Step 5: Finding the best tree size for our model

Step 6: Plotting our result on scatter plot
 Comparison by
Train Test Split

Random Tree Regressor

Train Test R2 Score

88 12 81.87%

78 22 79.17%

68 32 79.32%
 Comparison by
Train Test Split

Decision Tree Regressor

Train Test R2 Score

88 12 64.18%

78 22 58.89%

68 32 53.50%
 Comparison by
Train Test Split

Models Train Test R2 Score

Decision Tree 88 12 64.18%

Random Forest 88 12 81.87%

Scope of •Gameplay Mechanics and Design:
Analyzing how the game mechanics
Analysis 01 work, the level design, player
interactions, and overall gameplay
experience.

Narrative and Storytelling: Evaluating

the quality of the game's story,
characters, and world-building.
02

Visual and Audio Design:

Examining the game's
03 graphics, art style,
animation, and visual effects.