Module Code & Module Title

CU6051NT – Artificial Intelligence

Assessment Weightage & Type

Artificial Intelligence (25%)

Year and Semester

2020-21 Autumn

Student Name: Yubraj Shrestha

London Met ID: 20048545

College ID:np05cp4s210098@iic.edu.np

Assignment Submission Date: 2022-12-14

I confirm that I understand my coursework needs to be submitted online via Google Classroom under the relevant
module page before the deadline for my assignment to be accepted and marked. I am fully aware that late
submissions will be treated as non-submission and a mark of zero will be awarded.
Table of Contents
1. Introduction ............................................................................................................... 1

Explanation of the chosen problem domain ................................................................. 2

Cold Start Problem ...................................................................................................... 3

Synonymy .................................................................................................................... 3

Privacy ......................................................................................................................... 3

Sparsity........................................................................................................................ 3

2. Back Ground ............................................................................................................. 4

Collaborative Filtering .................................................................................................. 4

Content Based Filtering ............................................................................................... 5

3. Solution ..................................................................................................................... 6

Algorithm ..................................................................................................................... 7

Pseudocode ................................................................................................................. 8

Flowchart ..................................................................................................................... 9

4. Conclusion .............................................................................................................. 10

Analysis of work done ................................................................................................ 10

How the solution addresses real world problems ...................................................... 11

Further Work .............................................................................................................. 11

References .................................................................................................................... 12

Table of Figures
Figure 1: Example of K-Means Clustering ....................................................................... 6
Figure 2: Flowchart of K-Means Clustering. .................................................................... 9
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

1. Introduction
Artificial intelligence (AI) refers to the simulation of human intelligence in machines
programmed to think like humans and mimic their behavior. The term can also be
applied to any machine exhibiting properties related to the human mind, such as:
Learning and problem solving.

An ideal characteristic of artificial intelligence is its ability to streamline and execute

actions that are most likely to achieve a specific goal. A subset of artificial intelligence is
machine learning (ML). It refers to the concept that computer programs can
automatically learn and adapt to new data without human assistance. Deep learning
techniques enable this automatic learning by ingesting vast amounts of unstructured
data such as text, images, and videos. An ideal characteristic of artificial intelligence is
its ability to streamline and execute actions that are most likely to achieve a specific
goal. A subset of artificial intelligence is machine learning (ML). It refers to the concept
that computer programs can automatically learn and adapt to new data without human
assistance. Deep learning techniques enable this automatic learning by ingesting vast
amounts of unstructured data such as text, images, and videos.

From the user's perspective, it is designed to meet the user's needs in the shortest
possible time. For example, the type of content you watch on Netflix or Hulu. People
who only watch Korean dramas will only see related titles, but those who like action
shows this on the home screen.

1
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Explanation of the chosen problem domain

A recommendation system is an artificial intelligence or AI algorithm, usually associated
with machine learning, that uses huge data to suggest or recommend additional
products to customers. Recommendation system are very useful as they help users to
discover products and services. (Nvidia, 2022) The recommendation system deals with
a large volume of information present by filtering the most important information based
on the data provided by the user and other factors that take care of the user’s
preference and interest. (Nvidia, 2022)

Recommendation system process a large number of information which is very much

difficult to handle and as for the movie recommendation system, the system
receives the data from the user and provide the user similar products. It filters out all
the non-similarities movies and provide the similar one.

A recommender system is a type of information filtering system. By drawing from huge

data sets, the system’s algorithm can pinpoint accurate user preferences. Once you

2
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

know what your users like, you can recommend them new, relevant content. And that’s
true for everything from movies and music, to romantic partners.

Netflix, YouTube, Tinder, and Amazon are all examples of recommender systems in
use. The systems entice users with relevant suggestions based on the choices they
make.

Cold Start Problem

A recommender system is a type of information filtering technology that aims to provide
information that is likely to be of interest to users. A cold start problem occurs when the system
cannot establish a relationship between a user and an item that does not have enough data.

Synonymy
Synonymy is the tendency of very similar articles to have different names or entries. Most
recommendation systems have difficulty distinguishing between closely related items such as
baby clothes and baby clothes.

Privacy
Providing personal information to the recommendation system leads to data problems

Privacy and Security. Users are reluctant to provide data to affected recommender systems

data security issues.

Sparsity
However, all the proposed techniques require a rich history of interactions, especially in
systems where the number of users, the number of items, and the number of observed ratings
profoundly affect the performance. system capacity. This is called an analysis problem.

3
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

2. Back Ground
To make this project of the movie recommendation system i did a lot if research. as now
online movie streaming has become popular nowadays, instead of going into movie
center you can watch movies online of your choice, by checking your browsing history
movie recommendation system will provide you the movies similar to your choice. many
algorithms were studied while carrying out this project.

Netflix, YouTube, Tinder, and Amazon are all examples of recommender systems in
use. The systems entice users with relevant suggestions based on the choices they
make.

In recommendation system there are two approaches, they are collaborative Filtering
and content Based filtering.

Collaborative Filtering
Collaborative filtering filters information using interactions and data collected by the
system from other users. It is based on the idea that people who have already agreed in
their assessment of certain items are likely to agree again in the future.

The concept is very simple, when we want to find a new movie to watch, we often ask
friends for recommendations. Naturally, we trust more recommendations from friends
with similar interests to us.

Most of the collaborative filtering systems apply the so-called similarity index-based
technique. In the neighborhood-based approach, several users are selected based on
their similarity to the active user. Inference for active users is done by averaging the
ratings of selected users.

The collaborative filtering system focuses on the relationship between users and items.
The similarity of items is determined by the similarity of ratings of those items by users
who have rated both items.

Collaborative methods are often developed using utility matrices. The task of the
proposed model is to learn a function that predicts the usefulness of the fit or similarity
for each user. Utility matrices are often very sparse, huge, and have suppressed values.
4
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Content Based Filtering

Content-based filtering is a common technique of referrer or referrer systems. The
content or properties of the things you like are called "content".

Here, the system uses your characteristics and preferences to suggest things you might
like. It uses the information you provide on the internet and what they can gather, then
they make recommendations based on that.

The goal of content-based filtering is to rank products for specific keywords, find out
what customers like, search for those terms in the database, and then recommend
similar things.

This type of recommendation system relies heavily on user-supplied input, some

common examples include Google, Wikipedia, etc. For example, when a user searches
for a group of keywords, Google will display all the entries that include those keywords.
The video below explains how the content-based recommendation engine works.

5
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

3. Solution
Clustering is the task of dividing the data points into a number of groups such that data
points in the same groups are more similar to other data points in the same group and
dissimilar to the data points in the group. (GeekForGeeks, 2022)

K-means clustering is a unsupervised learning algorithm that is used to solve the

clustering problems in machine learning. K-Means algorithm makes the group of the
unlabeled dataset into k clusters in such a way that each dataset belongs on the group
that has similar properties. Here the k defines the number of pre-defined clusters.

The main task of K-Means clustering is to determines the best value for K center points
or centroids by an iterative process and assigns each data point to its closest k-center
and those data points which are near to the particular k-center, create a cluster.
(GeekForGeeks, 2022)

The working of the diagram is shown by given figure:

Figure 1: Example of K-Means Clustering

6
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Algorithm
K-Means clustering is a centroid-based algorithm, where each cluster is related with a
centroid. This algorithm minimizes the sum of distance between the data point and their
corresponding clusters. The algorithm takes the unlabeled dataset as input, splits the
dataset into k-number of clusters, and repeats the process until it does not find the best
clusters. The value of k should be predetermined in this algorithm. (Javatpoint, 2021)

The algorithm that is used in K-Means clustering is:

Step 1: Choose the value of K which is number of clusters.

Step 2: Select K data at random from the dataset as an initial cluster centroid.

Step 3: For each datapoint:

Step 3.1: Assign the datapoint to the closest centroid.

Step 3.2: Compute the distance between the datapoint and the cluster centroid.

Step 4: For each cluster calculate the new mean based on the datapoints in the cluster.

Step 5: Repeat step 3 and step 4 until the mean of the clusters stops changing or

maximum number of Iteration reached.

7
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Pseudocode
Choose number of clusters, K

Initialize K centroids at random

FOR each datapoint

Repeat

Assign each datapoint to the closest centroid

Compute the distance between the datapoint and the cluster centroid

Until The centroids don’t change

END

8
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Flowchart

Figure 2: Flowchart of K-Means Clustering.

9
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

4. Conclusion
Analysis of work done

S.N Task Status

1 Research on Artificial Intelligence Completed
2 Research on Recommendation System Completed
3 Research on chosen topic Completed
4 Problem Statement of Chosen Topic Completed
5 Research on work done method Completed
6 Similar system review Completed
7 Review & analyzing existing work Completed
8 Research solution of selected Completed
9 Flowchart & Pseudocode Completed
10 Implementing Coding Incomplete
11 Testing Project Incomplete

This is the first coursework of the artificial intelligence so it was quite tough to do the
coursework. I faced so much problem while choosing the topic for this coursework but
finally with the help of my research I was able to overcome the problem. I have
researched a lot and chose movie recommendation system for the research topic. I
have used the K-Means Clustering algorithm to find the solution for movie
recommendation system and have create the pseudocode and flowchart of the
algorithm was developed to ease the coding part in future.

10
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

How the solution addresses real world problems

The movie recommendation system is used to analyze the past preferences of the user
concerned and then it uses the same information to try to find similar movies.

Further Work
After this course work, I have learned more about recommendation system so I will start
developing the model by using python programming language. I will be focused on
making my system accurate.

11
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

References
(2021). Retrieved from Javatpoint: https://www.javatpoint.com/k-means-clustering-
algorithm-in-machine-learning

(2022). Retrieved from Nvidia: https://www.nvidia.com/en-us/glossary/data-

science/recommendation-system/

(2022). Retrieved from GeekForGeeks:

https://www.google.com/search?q=clustering+in+machine+learning&oq=clusturin
g+in+&aqs=chrome.2.69i57j0i10i512l9.7465j0j4&sourceid=chrome&ie=UTF-8

(2022). Retrieved from LabelYourData: https://labelyourdata.com/articles/movie-

recommendation-with-machine-
learning#:~:text=How%20does%20it%20work%3F,movie%20recommendations
%20for%20the%20user.

Khandual, S. (2022). K-Means Clustring. Retrieved from

https://www.niser.ac.in/~smishra/teach/cs460/2020/lectures/lec22/

Kordík, P. (2021). Retrieved from Medium: https://medium.com/recombee-

blog/machine-learning-for-recommender-systems-part-1-algorithms-evaluation-
and-cold-start-6f696683d0ed

Movie Recommendation System. (2022). MyGreatLearning, 5. Retrieved from

https://www.mygreatlearning.com/blog/masterclass-on-movie-recommendation-
system/

12
CU6051NT
YUBRAJ SHRESTHA ARTIFICIAL INTELLEGENCE

Singh, A. (2022). Movie Recommendation System. Naukri Learning, 5. Retrieved from

https://www.naukri.com/learning/articles/movie-recommendation-system-using-
machine-learning/

Singh, S. (2022). K-Means Clustering. India: DataDrivenInvestor. Retrieved from

https://medium.datadriveninvestor.com/k-means-clustering-b89d349e98e6

13
CU6051NT