MOVIE RECOMMENDER SYSTEM

A PROJECT REPORT
Submitted by
Shekhar 20BCS9911
Sanya Pawar 20BCS9879
Tushar Mishra 20BCS9962

in partial fulfilment for the award of the degree of

Bachelor of Engineering
IN

Computer Science and Engineering

Chandigarh University
May, 2022
 BONAFIDE CERTIFICATE

Certified that this project report “Movie Recommender System” is the

<<Signature of the Head of the Department>> <<Signature of the

<<Name>> <<Name>>
HEAD OF THE SUPERVISOR
DEPARTMENT

<<Academic Designation>>

<<Department>> <<Department>>

Submitted for the project viva-voce examination held on

INTERNAL EXAMINER EXTERNAL

replacing' system ‘with a reverse similar as platform or machine), is a

class of information filtering system that seeks to prognosticate the"

standing “or" preference “a stoner would give to an item.

Recommender systems are used in a variety of areas, with generally

recognised exemplifications taking the form of playlists creators for

videotape and music services, product recommenders for online stores,

or content recommender for social media platforms and an open web

content recommender.

These systems can operate with a single input, such as music, or

multiple inputs, both within and across platforms, such

as news, books, and search. There are also popular recommender

systems for specific motifs like caffs and online courting. Recommender

systems have also been developed to explore exploration papers and

experts, collaborators, and fiscal services.

Our project will be like movie website where users will give reviews

and that can help other users to find movies they are looking for. We

will recommend movies and web shows according to user’s input like

what kind of movie you want to watch. We will be using movies and

cast data from a source file that we imported from a website. A well-
built recommender system can lead to an excellent customer experience,

which is why understanding how they work is highly important from a

data science perspective. Recommender systems were simple in their

early days, and have since evolved into more complex models. This will

help user to find movies they are looking for.

Table of Contents
Sr. No. Topic Page No.

1.
Introduction 1-6

2. Background 7-10

3. Designs 11-12

4. Screenshots 13

5. Related Work 14-19

7. Conclusion 20-21

INTRODUCTION
Recommender systems are the systems that are designed to recommend effects

to the stoner grounded on numerous different factors. These systems

prognosticate the most likely product that the druggies are most likely to buy

and are of interest to. Companies like Netflix, Amazon, etc. use recommender

systems to help their druggies to identify the correct product or pictures for

them.

Both the druggies and the services handed have served from these kinds of

systems. The quality and decision- making process has also bettered through

these kinds of systems.

Benefits of recommendation -

• Help users find items of interest.

• Help item vendors deliver items to the correct users.

• Identify the products most relevant to users.

•Personalizedcontent.

• Helping websites improve user engagement.

I would like to end my blog by saying that

the recommender system has changed the whole scenario to

1
make it easier for users to choose the choices and interests they want. It

recommends user personalized content. There are various other platforms where

these systems are currently used. 

In our blog, we discussed recommender systems, their types, and the different

methods used in recommender systems. However, in the future, there may be

many advances in the technology that can be expected as

there are many problems with the recommender system.

Recommender systems aim to predict users' interests and recommend product

items that quite likely are interesting for them. They are among the most

powerful machine learning systems that online retailers implement in order to

drive sales.

Data required for recommender systems stems from explicit user ratings after

watching a movie or listening to a song, from implicit search engine queries

and purchase histories, or from other knowledge about the users/items

themselves.

2
 Why do we need recommender systems?

Companies using recommender systems focus on increasing sales as a result of

very personalized offers and an enhanced customer experience.

Recommendations typically speed up searches and make it easier for users to

access content they’re interested in, and surprise them with offers they would have

never searched for.

What is more, companies are able to gain and retain customers by sending out

emails with links to new offers that meet the recipients' interests, or suggestions of

films and TV shows that suit their profiles.

The user starts to feel known and understood and is more likely to buy additional

products or consume more content. By knowing what a user wants, the company

gains competitive advantage and the threat of losing a customer to a competitor

decreases.

Providing that added value to users by including recommendations in systems and

products is appealing. Furthermore, it allows companies to position ahead of their

competitors and eventually increase their earnings.

3
 How does a recommender system work?

Recommender systems function with two kinds of information:

 Characteristic information. This is information about items (keywords,

categories, etc.) and users (preferences, profiles, etc.).

 User-item interactions. This is information such as ratings, number of

purchases, likes, etc.

Based on this, we can distinguish between three algorithms used in recommender

systems:

 Content-based systems, which use characteristic information.

 Collaborative filtering systems, which are based on user-item interactions.

 Hybrid systems, which combine both types of information with the aim of

avoiding problems that are generated when working with just one kind.

Next, we will dig a little deeper into content-based and collaborative filtering

systems and see how they are different.

4
 Content-based systems
These systems make recommendations using a user's item and profile features.

They hypothesize that if a user was interested in an item in the past, they will once

again be interested in it in the future. Similar items are usually grouped based on

their features. User profiles are constructed using historical interactions or by

explicitly asking users about their interests. There are other systems, not

considered purely content-based, which utilize user personal and social data.

One issue that arises is making obvious recommendations because of excessive

specialization (user A is only interested in categories B, C, and D, and the system

is not able to recommend items outside those categories, even though they could

be interesting to them).

Another common problem is that new users lack a defined profile unless they are

explicitly asked for information. Nevertheless, it is relatively simple to add new

items to the system. We just need to ensure that we assign them a group according

to their features.

Collaborative filtering is currently one of the most frequently used approaches and

usually provides better results than content-based recommendations.

5
Some examples of this are found in the recommendation systems

of Youtube, Netflix, and Spotify.

These kinds of systems utilize user interactions to filter for items of interest. We

can visualize the set of interactions with a matrix, where each entry (i, j)

(i,j) represents the interaction between user ii and item jj. An interesting way of

looking at collaborative filtering is to think of it as a generalization

of classification and regression. While in these cases we aim to predict a variable

that directly depends on other variables (features), in collaborative filtering there

is no such distinction of feature variables and class variables.

6
 Background

Behind the fleetly adding fissionability of machines extremely serious

sweats lie, which has been made to reduce “disunion” between man and

machine. Decreasingly comfortable results have been created because

attempts have been made to understand people’s requirements and

epitomize the services handed by computers. The basics of recommender

systems were innovated by inquiries into cognition wisdom and information

reclamation, and its first incarnation was the Usenet communication system

created by Duke University in the alternate half of the 1970s, where

druggies were suitable to partake textual content with each other. These

were distributed into newsgroups and groups for easier hunt, but it wasn't

directly erected on or targeted the preferences of druggies.

The first known similar result was the computer librarian Grundy, which

first canvassed druggies about their preferences and also recommended

books to them considering this information. Grounded on the information

collected the system allocated the stoner into a conception group using a

rather primitive system, therefore recommending the same books to all

persons in the same group.

7
For further information about the results of Grundy’s result and its

fissionability among druggies, see Rich’s 1979 composition. This approach

may feel a little outdated moment, but at the time it was a paradigm shift in

automated services, since it was personalised. It's important to note that this

corner has not been reached by all web shops, indeed now.

Recommender systems are based on a variety of approaches such as content

based collaborative approach hybrid. Furthermost movie recommendation

systems are centred on collaborative filtering and clustering. In movie

recommender systems the user is asked to rate the movies which user has

already seen then these ratings are applied to recommend other movies to

the user that user has not perceived by utilizing collaborative filtering that is

based on similar ratings. Collaborative filtering is tremendously spreading

in such a way that this approach influences most of the recommender

systems. Collaborative filtering majorly classified into two principal classes

such as memory-based collaborative filtering and model based collaborative

filtering. Memory-based collaborative filtering explores for nearest

neighbours in the user space for an active user and dynamically recommend

the movies. The shortcomings related to this method are computation

complexity and data sparsity.

8
Many authors tried to reduce this computational complexity and memory

bottleneck issues such as in item based collaborative filtering technique, in

which relations between items were computed for neighbourhood region

around a target object. They showed in their empirical studies that item-

based method could decrease the time of computation as well as deliver

rationally correct prediction and accurateness. Model-based collaborative

technique produces a prebuilt model to collect rating patterns based on the

database of users and ratings that can treat the issues of data sparsity and

scalability. Model-based collaborative filtering is time-consuming and its

offline in nature. Clustering based techniques are broadly used in movie

recommendation systems to reduce the problem of scalability. Various

researchers applied clustering-based methods on recommender systems that

delivered expert recommendations. The purpose of clustering is to partition

objects into groups known as clusters in such a way that two objects within

the same cluster have a minimum distance between them to identify similar

objects then clustering process is performed offline to build the model.

When a target user arrived, the online module allocates a cluster with a

substantial similarity weight to the user, and

9
the prediction rating of a specified item is computed based on the same

cluster members instead of searching whole user space.

The k-nearest neighbour (kNN) algorithm is the orientation algorithm in

collaborative filtering recommendation process which is applied in

recommendation process. kNN based recommender systems for

collaborative filtering recommendation process are reliable and with precise

recommendations. A bio-inspired algorithm such as cuckoo search has

exclusive background sensing abilities and employ a special method to

facilitate the evolution of continuing resolutions into novel and quality

recommendations by generating clusters with reduced time as discussed in

next section.

10
 Designs

Data Flow Diagram:

11
Flow Chart:

12
Screenshots:

13
 Related work
The model building process can be done using machine learning or data mining

techniques. These techniques can quickly recommend a set of items for the fact that

they use pre-computed model and they have proved to produce recommendation

results that are similar to neighbourhood-based recommender techniques. Examples

of these techniques include Dimensionality Reduction technique such as Singular

Value Decomposition (SVD), Matrix Completion Technique, Latent Semantic

methods, and Regression and Clustering. Model-based techniques analyze the user-

item matrix to identify relations between items; they use these relations to compare

the list of top-N recommendations. Model based techniques resolve

the sparsity problems associated with recommendation systems.

The use of learning algorithms has also changed the manner of recommendations

from recommending what to consume by users to recommending when to actually

consume a product. It is therefore very important to examine other learning

algorithms used in model-based recommender systems:

Association rule: Association rules mining algorithms [49] extract rules that

predict the occurrence of an item based on the presence of other items in a

transaction. For instance, given a set of transactions, where each transaction

is a set of items, an association rule applies the form A → B, where A and

14
 B are two sets of items [50]. Association rules can form a very compact

representation of preference data that may improve efficiency of storage as

well as performance. Also, the effectiveness of association rule for

uncovering patterns and driving personalized marketing decisions has been

known for sometimes [2]. However, there is a clear relation between this

method and the goal of a Recommendation System but they have not

become mainstream.

Clustering: Clustering techniques have been applied in different domains

such as, pattern recognition, image processing, statistical data analysis and

knowledge discovery [51]. Clustering algorithm tries to partition a set of data

into a set of sub-clusters in order to discover meaningful groups that exist

within them [52]. Once clusters have been formed, the opinions of other

users in a cluster can be averaged and used to make recommendations for

individual users. A good clustering method will produce high quality clusters

in which the intra-cluster similarity is high, while the inter-cluster similarity

is low. In some clustering approaches, a user can have partial participation in

different clusters, and recommendations are then based on the average across

the clusters of participation which is weighted by degree of

15
participation [53]. K-means and Self-Organizing Map (SOM) are the most

commonly used among the different clustering methods. K-means takes an

input parameter, and then partitions a set of n items into K clusters [54]. The

Self-Organizing Map (SOM) is a method for an unsupervised learning, based

on artificial neurons clustering technique [55]. Clustering techniques can be

used to reduce the candidate set in collaborative-based algorithms.

Decision tree: Decision tree is based on the methodology of tree

graphs which is constructed by analyzing a set of training examples for

which the class labels are known. They are then applied to classify

previously unseen examples. If trained on very high quality data, they have

the ability to make very accurate predictions [56]. Decision trees are more

interpretable than other classifier such as Support Vector machine (SVM)

and Neural Networks because they combine simple questions about data in

an understandable manner. Decision trees are also flexible in handling items

with mixture of real-valued and categorical features as well as items that

have some specific missing features.

Artificial Neural network: ANN is a structure of many connected neurons

(nodes) which are arranged in layers in systematic ways.

16
The connections between neurons have weights associated with them

depending on the amount of influence one neuron has on another.

There are some advantages in using neural networks in some special problem

situations. For example, due to the fact that it contains many neurons and

also assigned weight to each connection, an artificial neural network is quite

robust with respect to noisy and erroneous data sets [57]. ANN has the ability

of estimating nonlinear functions and capturing complex relationships in data

sets also, they can be efficient and even operate if part of the network fails.

The major disadvantage is that it is hard to come up with the ideal network

topology for a given problem and once the topology is decided this will act as

a lower bound for the classification error.

Link analysis: Link Analysis is the process of building up networks of

interconnected objects in order to explore pattern and trends [58]. It has

presented great potentials in improving the accomplishment of web search.

Link analysis consists of PageRank and HITS algorithms. Most link analysis

algorithms handle a web page as a single node in the web graph [59].

Regression: Regression analysis is used when two or more variables are

thought to be systematically connected by a linear relationship.

17
It is a powerful and diversity process for analyzing associative relationships

between dependent variable and one or more independent variables. Uses of

regression contain curve fitting, prediction, and testing systematic hypotheses

about relationships between variables. The curve can be useful to identify a

trend within dataset, whether it is linear, parabolic, or of some other forms.

Bayesian Classifiers: They are probabilistic framework for solving

classification problems which is based on the definition of conditional

probability and Bayes theorem. Bayesian classifiers [36] consider each

attribute and class label as random variables. Given a record of N features

(A1, A2, …, AN), the goal of the classifier is to predict class Ck by finding the

value of Ck that maximizes the posterior probability of the class given the

data P(Ck|A1, A2, …, AN) by applying Bayes’ theorem, P(Ck|A1, A2,

…, AN) ∝ P(A1, A2, …, AN|Ck)P(Ck). The most commonly used Bayesian

classifier is known as the Naive Bayes Classifier. In order to estimate the

conditional probability, P(A1, A2, …, AN|Ck), a Naive Bayes Classifier

assumes the probabilistic independence of the attributes that is, the presence

or absence of a particular attribute is unrelated to the presence or absence of

any other.

18
This assumption leads to P(A1, A2, …, AN|Ck) = P(A1|Ck)P(A2|Ck)… P(AN|

Ck). The main benefits of Naive Bayes classifiers are that they are robust to

isolated noise points and irrelevant attributes, and they handle missing values

by ignoring the instance during probability estimate calculations. However,

the independence assumption may not hold for some attributes as they might

be correlated. In this case, the usual approach is to use Bayesian Networks.

Bayesian classifiers may prove practical for environments in which

knowledge of user preferences changes slowly with respect to the time

needed to build the model but are not suitable for environments in which

users preference models must be updated rapidly or frequently. It is also

successful in model-based recommendation systems because it is often used

to derive a model for content-based recommendation systems.

19

Conclusion
Recommender systems are a important new technology for rooting fresh

value for a business from its stoner databases. These systems help druggies

find particulars they want to buy from a business. Recommender systems

profit druggies by enabling them to find particulars they like. Again, they

help the business by generating further deals. Recommender systems are

fleetly getting a pivotal tool in E-commerce on the Web. Recommender

systems are being stressed by the huge volume of stoner data in being

commercial databases, and will be stressed indeed more by the adding

volume of stoner data available on the Web. New technologies are

demanded that can dramatically ameliorate the scalability of recommender

systems.

In this paper we presented and experimentally estimated a new algorithm

for CF- grounded recommender systems. Our results show that item-

grounded ways hold the pledge of allowing CF- grounded algorithms to

gauge to large data sets and at the same time produce high- quality

recommendations.

Content- grounded styles are grounded on the similarity of movie attributes.

Using this type of recommender system, if a stoner watches one movie,

analogous pictures are recommended.

For illustration, if a stoner watches a comedy movie starring Adam Sandler,

the system will recommend them pictures in the same kidney or starring the

same actor, or both. With this in mind, the input for erecting a content-

grounded recommender system is movie attributes.

Recommender systems are a powerful new technology for extracting additional

value for a business from its user databases. These systems help users find items

they want to buy from a business. Recommender systems benefit users by enabling

them to find items they like. Conversely, they help the business by generating more

sales. Recommender systems are rapidly becoming a crucial tool in E-commerce on

the Web. Recommender systems are being stressed by the huge volume of user data

in existing corporate databases, and will be stressed even more by the increasing

volume of user data available on the Web. New technologies are needed that can

dramatically improve the scalability of recommender systems.

In this paper we presented and experimentally evaluated a new algorithm for CF-

based recommender systems. Our results show that item-based techniques hold the

promise of allowing CF-based algorithms to scale to large data sets and at the same

time produce high-quality recommendations.